© 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. 20747
    Prev
    Next
    INDEX
    Explanations

    predictions of items

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

    circuitry estimates safety features size privacy

    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
    ಳಿ
    0.47
     군
    0.45
    噴
    0.45
    تان
    0.43
    მასრულ
    0.43
    紋
    0.41
    मॉन
    0.41
    뇰
    0.41
     পেট্র
    0.40
    gün
    0.40
    POSITIVE LOGITS
    UM
    0.45
    OC
    0.45
     because
    0.44
    IB
    0.43
    RU
    0.43
     erreur
    0.43
     payee
    0.43
    があって
    0.42
     educated
    0.42
     OC
    0.42
    Activations Density 0.000%

    No Known Activations