© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16394
    Prev
    Next
    INDEX
    Explanations

    articles and common words followed by specific nouns

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

    Assistant Voice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     democracies
    0.49
    Влади
    0.49
     ecz
    0.46
    куса
    0.46
    inama
    0.46
    저
    0.46
    entrée
    0.45
     renovación
    0.45
    颢
    0.45
     parada
    0.45
    POSITIVE LOGITS
     Man
    0.49
     Manc
    0.48
     Character
    0.48
     NU
    0.48
     S
    0.47
     Ginsburg
    0.47
     Diaz
    0.47
     Did
    0.46
     Decre
    0.46
    icher
    0.46
    Activations Density 0.000%

    No Known Activations