© 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. 1741
    Prev
    Next
    INDEX
    Explanations

    for Cotton

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

    primary forms

    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
    AQP
    0.47
    Penumpang
    0.45
     STEELS
    0.44
     EGFR
    0.44
     Srbiji
    0.44
     menek
    0.43
    \}$.
    0.43
    Wrapper
    0.42
     eTo
    0.42
     pointillés
    0.41
    POSITIVE LOGITS
     रिव
    0.43
    易
    0.43
    good
    0.42
     хорошее
    0.40
    デザイン
    0.40
     designed
    0.39
     easy
    0.39
    easy
    0.39
     Designed
    0.38
     $[\
    0.38
    Activations Density 0.000%

    No Known Activations