© 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. 29024
    Prev
    Next
    INDEX
    Explanations

    sc words

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

    scanned, scarcity, scikit, scoring, scrambled

    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
    на
    0.62
    oksatta
    0.60
    sef
    0.59
    zeg
    0.57
    swald
    0.55
     Elovl
    0.55
    esa
    0.54
    鵠
    0.53
    estone
    0.53
    onas
    0.53
    POSITIVE LOGITS
     sc
    0.75
     scr
    0.74
    Sc
    0.71
    蝎
    0.70
     ска
    0.69
     एससी
    0.68
     scavenger
    0.68
     intereses
    0.67
    SCR
    0.66
     sco
    0.66
    Activations Density 0.140%

    No Known Activations