© 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. 78335
    Prev
    Next
    INDEX
    Explanations

    proper noun beginnings

    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_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
    轰隆
    -0.95
     detal
    -0.92
    aní
    -0.91
    eeee
    -0.91
     Decreto
    -0.91
    baseURL
    -0.89
     sampel
    -0.89
     plata
    -0.88
     risque
    -0.88
    POSITIVE LOGITS
     County
    1.06
     didn
    0.98
    嬅
    0.93
     soportar
    0.91
    Didn
    0.89
     śnie
    0.89
     mwenye
    0.89
    engg
    0.88
     acompañar
    0.88
     jų
    0.86
    Activations Density 0.009%

    No Known Activations