© 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. 76866
    Prev
    Next
    INDEX
    Explanations

    words following certain common tokens

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

    social engineering attempts

    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
     當
    0.45
    樓
    0.42
     gdzie
    0.41
     النرويج
    0.40
    GROW
    0.40
     семье
    0.40
    Washington
    0.39
     councils
    0.39
     Cheltenham
    0.39
    usehen
    0.39
    POSITIVE LOGITS
    实例
    0.46
     Procedure
    0.45
    lių
    0.42
     Instance
    0.41
    ″]
    0.41
    ğinin
    0.41
    ತಕ್ಕ
    0.40
     citing
    0.40
     হবেনা
    0.40
    Bună
    0.40
    Activations Density 0.001%

    No Known Activations