© 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. 34454
    Prev
    Next
    INDEX
    Explanations

    exchange for

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    轢
    -0.91
    hommes
    -0.85
    ={({
    -0.84
    busca
    -0.84
     divest
    -0.83
    Brah
    -0.82
    越高
    -0.82
    ftances
    -0.81
     botanique
    -0.81
    合适的
    -0.79
    POSITIVE LOGITS
     quid
    0.96
     Satisfied
    0.90
     agreed
    0.88
     otherwise
    0.88
     agreeing
    0.87
    forRoot
    0.86
    unlock
    0.86
    otherwise
    0.85
    حة
    0.85
     reluctantly
    0.84
    Activations Density 0.040%

    No Known Activations