© 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. 104797
    Prev
    Next
    INDEX
    Explanations

    knuckle protector

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

    decision, housekeeping, popular, Powder, Civil, without, Upgrade, external

    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
    W
    0.50
     in
    0.47
    </code>
    0.41
     Mann
    0.41
     imm
    0.40
    MM
    0.40
    ня
    0.39
    楕
    0.38
    一緒
    0.38
    daughters
    0.38
    POSITIVE LOGITS
     公司
    0.56
    ής
    0.50
     terraza
    0.49
    यी
    0.49
    ोरा
    0.47
     społec
    0.47
     省
    0.47
    rição
    0.47
    oyens
    0.47
     व्यवसाय
    0.46
    Activations Density 0.001%

    No Known Activations