© 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. 172711
    Prev
    Next
    INDEX
    Explanations

    daughter died

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

    to large

    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
    Day
    0.53
     компен
    0.52
    Mark
    0.51
    Qu
    0.50
    Sw
    0.50
    А
    0.50
    Rounding
    0.49
    Substitute
    0.49
    QU
    0.48
    Q
    0.48
    POSITIVE LOGITS
     skele
    0.50
     perchè
    0.48
     lieber
    0.48
     forested
    0.46
     mâles
    0.46
     tease
    0.46
     jugu
    0.46
     eerst
    0.45
     ausgewählt
    0.45
     stále
    0.45
    Activations Density 0.001%

    No Known Activations