© 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. 93568
    Prev
    Next
    INDEX
    Explanations

    exercises and theorems

    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
    сибир
    -0.82
    купить
    -0.80
    ITT
    -0.80
     የ
    -0.79
     זו
    -0.79
     dniu
    -0.79
    İM
    -0.77
     собы
    -0.77
     Bod
    -0.76
     Sed
    -0.75
    POSITIVE LOGITS
     bangun
    0.94
    ᴾ
    0.93
     
    0.82
    siella
    0.81
     lightly
    0.79
    BrowserModule
    0.78
     personali
    0.76
     Personalis
    0.76
     speciali
    0.76
    otas
    0.76
    Activations Density 0.003%

    No Known Activations