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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55829
    Prev
    Next
    INDEX
    Explanations

    programming libraries and formats

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

    The neuron is highly sensitive to code‐style identifiers and API call tokens (e.g. function/class names and other programming‐specific keywords).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     with
    -1.64
     Zeitpunkt
    -0.79
     time
    -0.77
     Schuyler
    -0.74
    дела
    -0.71
    Sébastien
    -0.70
     Schles
    -0.69
    呐
    -0.68
    entr
    -0.68
     считать
    -0.68
    POSITIVE LOGITS
    regards
    1.03
    HasForeignKey
    1.00
    regard
    0.90
    为例
    0.90
    bolista
    0.88
    })->
    0.85
    Прият
    0.85
    🍡
    0.84
    ATURA
    0.83
    셉
    0.83
    Activations Density 0.279%

    No Known Activations