© 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. 231181
    Prev
    Next
    INDEX
    Explanations

    completion, patrol, reservation

    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
    s
    0.65
     an
    0.53
    is
    0.47
     monoc
    0.47
    ీ
    0.47
    es
    0.47
    sees
    0.45
    ens
    0.45
     depiction
    0.45
    eval
    0.44
    POSITIVE LOGITS
    堊
    0.54
    ഗ്രഹം
    0.50
    োরের
    0.49
     острова
    0.48
    ươ
    0.47
    durationType
    0.46
    ựa
    0.46
    스템
    0.46
     dağı
    0.45
     Orion
    0.45
    Activations Density 0.000%

    No Known Activations