© 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. 34-GEMMASCOPE-RES-131K
    7. 93267
    Prev
    Next
    INDEX
    Explanations

    documentation comments

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

    The neuron detects the asterisk markers used at the start of lines in block‐style (e.g., Javadoc or PHPDoc) comments.

    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
    //};
    -0.98
    Čo
    -0.97
    /**
    -0.95
    canActivate
    -0.93
     効果
    -0.93
    providedIn
    -0.93
    方がいい
    -0.93
     poté
    -0.93
    おはよう
    -0.92
    рії
    -0.91
    POSITIVE LOGITS
     @
    3.47
    @
    2.42
    ,@
    1.45
    (@
    1.42
     {@
    1.37
     (@
    1.30
     <
    1.28
    ">@
    1.26
    =@
    1.25
    .@
    1.21
    Activations Density 0.012%

    No Known Activations