© 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. 22-GEMMASCOPE-RES-131K
    7. 72032
    Prev
    Next
    INDEX
    Explanations

    latex document class

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

    The neuron is triggered by opening curly‐brace tokens “{” (as used in LaTeX command arguments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    <bos>
    -3.09
    などが
    -2.50
     
    -2.22
     in
    -2.20
    は
    -1.99
    i
    -1.95
    などは
    -1.93
    を
    -1.93
     that
    -1.82
     from
    -1.75
    POSITIVE LOGITS
    蠵
    2.56
     comical
    2.53
    為に
    2.33
    薅
    2.30
    %")
    2.28
    
    2.23
     luxurious
    2.22
    憮
    2.19
     parlak
    2.16
    喏
    2.14
    Activations Density 0.011%

    No Known Activations