© 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. 114413
    Prev
    Next
    INDEX
    Explanations

    you or your

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

    understand these

    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
    汅
    0.53
     scepticism
    0.48
     प्रणाली
    0.47
     ადგილ
    0.47
     meagre
    0.46
    imely
    0.46
     днем
    0.45
    লোকে
    0.45
    🏿
    0.45
     хими
    0.45
    POSITIVE LOGITS
     but
    0.46
     Nagy
    0.45
     Burrow
    0.45
     For
    0.45
     Presses
    0.45
     on
    0.45
     Fonds
    0.44
     Rider
    0.44
    žu
    0.44
     for
    0.44
    Activations Density 0.001%

    No Known Activations