© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92217
    Prev
    Next
    INDEX
    Explanations

    just need

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

    Warning: May cause

    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
    KeyUp
    0.48
    ángulos
    0.47
    Metadata
    0.47
    զ
    0.46
    Snapshot
    0.46
    Ꮷ
    0.45
     iemand
    0.45
    ంగ
    0.45
    謐
    0.45
    führer
    0.44
    POSITIVE LOGITS
    -
    0.52
    tt
    0.48
    allaitement
    0.43
     (:
    0.42
    uti
    0.41
     (${
    0.40
    oules
    0.40
    jax
    0.40
     &=\
    0.40
    achusetts
    0.39
    Activations Density 0.011%

    No Known Activations