© 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. 29653
    Prev
    Next
    INDEX
    Explanations

    many assets

    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
     onstage
    0.46
     gespielt
    0.43
    𒁍
    0.43
     देवता
    0.43
    টিও
    0.40
     també
    0.40
     MUSE
    0.39
     खिलाड़ियों
    0.39
     மாறிய
    0.38
     ollut
    0.38
    POSITIVE LOGITS
    金
    0.42
    ênd
    0.39
    δι
    0.38
    лах
    0.38
     Enrico
    0.38
    ↵
    0.36
    actose
    0.36
    ल्पन
    0.35
    Ahh
    0.35
    unications
    0.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.