© 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. 6679
    Prev
    Next
    INDEX
    Explanations

    temperature, Air, Click, Search

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

    Market order

    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
     كثير
    0.35
     affirme
    0.35
     appena
    0.32
     ربعه
    0.31
    ؟
    0.31
     entusias
    0.31
     ایمان
    0.30
    öyle
    0.30
     multimillion
    0.30
     plaintiff
    0.30
    POSITIVE LOGITS
    _
    0.46
    /
    0.44
    -
    0.37
    ри
    0.37
     and
    0.36
     分
    0.35
     of
    0.35
    and
    0.35
    -/
    0.35
    ID
    0.33
    Activations Density 0.035%

    No Known Activations