© 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. 112758
    Prev
    Next
    INDEX
    Explanations

    keywords, file types, code snippets

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

    whitespace or indentation preceding commas in lists or arrays in code.

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

    The neuron fires almost exclusively on individual items inside array literals (i.e. the comma‐separated elements in `[…]`).

    oai_token-act-pair · o4-miniTriggered 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
     $
    -1.91
    </h4>
    -1.53
    }
    -1.52
    1
    -1.50
    2
    -1.49
    "]
    -1.48
     For
    -1.46
    b
    -1.44
     it
    -1.36
    \\
    -1.36
    POSITIVE LOGITS
    hancers
    1.48
    颪
    1.45
    ቭ
    1.44
     eluc
    1.40
    達が
    1.37
     creativos
    1.37
     verdaderos
    1.36
    ,
    1.34
     obfusc
    1.32
     Какой
    1.31
    Activations Density 0.016%

    No Known Activations