© 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. 43734
    Prev
    Next
    INDEX
    Explanations

    of the

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

    detailed description of amenities

    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
    PSI
    0.43
    is
    0.42
    eer
    0.42
     imported
    0.41
    ők
    0.40
    많
    0.39
     very
    0.39
    ks
    0.39
    बहु
    0.39
     revolved
    0.39
    POSITIVE LOGITS
     学
    0.57
     管理
    0.53
     柄
    0.53
     売場面積
    0.50
    itanie
    0.50
     Ladakh
    0.48
     troughs
    0.48
     重量
    0.48
     অনুগ্রহ
    0.47
     Selbst
    0.47
    Activations Density 0.000%

    No Known Activations