© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112673
    Prev
    Next
    INDEX
    Explanations

    code blocks using keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    the assignment operator in programming code (specifically the left arrow `<-` used in languages like R, Go channels, and some functional programming languages).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the literal “<-” token (the left‐arrow operator).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the left-arrow (“<-”) operator in code, including receive/assignment/binding uses across programming languages.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ни
    -2.52
    と
    -2.48
    蘗
    -2.47
    u
    -2.41
    In
    -2.36
                
    -2.36
    幸好
    -2.33
    Even
    -2.31
    Three
    -2.30
    }
    -2.30
    POSITIVE LOGITS
    𐐀
    3.17
    寕
    2.98
    ﮨ
    2.94
    咴
    2.66
    䊉
    2.64
     are
    2.61
    卝
    2.56
    鉿
    2.48
    ﮦ
    2.44
     Перейти
    2.42
    Activations Density 0.002%

    No Known Activations