© 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. 162153
    Prev
    Next
    INDEX
    Explanations

    NTFS For, channels, patient, tile

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

    hear, pads, thoroughly, server, bodies, and

    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
    a
    0.53
     views
    0.52
     skies
    0.52
     shotgun
    0.48
     sky
    0.48
     by
    0.47
     gal
    0.47
     ujung
    0.47
     skóry
    0.47
     skins
    0.46
    POSITIVE LOGITS
    𒅴
    0.52
    ocardial
    0.46
     ایل
    0.46
    佾
    0.45
     الاستفهام
    0.45
    。「
    0.45
    児童
    0.45
    忱
    0.44
    ClCompile
    0.44
     کلب
    0.44
    Activations Density 0.000%

    No Known Activations