© 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. 163162
    Prev
    Next
    INDEX
    Explanations

    calendar, dont want, might earn, of course

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

    breakdown compare

    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
    way
    0.52
     अक्सर
    0.51
    &
    0.50
    \
    0.49
    买
    0.49
    н
    0.48
    often
    0.47
    *
    0.47
    C
    0.47
    _
    0.47
    POSITIVE LOGITS
    ClearedBy
    0.49
     Brownian
    0.49
    SystemCall
    0.47
     biologiques
    0.47
    TorpedoStore
    0.46
     sécr
    0.46
     BGPS
    0.45
     stabilité
    0.45
     colocadas
    0.45
     profesores
    0.45
    Activations Density 0.001%

    No Known Activations