© 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. 184692
    Prev
    Next
    INDEX
    Explanations

    brick liquid celebration

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

    maker

    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
    we
    0.52
     skillfully
    0.45
    馕
    0.45
    Г
    0.44
    У
    0.43
    uvad
    0.43
     Cytol
    0.43
     toler
    0.42
     fission
    0.42
    ្វី
    0.42
    POSITIVE LOGITS
    idikan
    0.49
     ダイヤ
    0.49
     צריך
    0.47
    ());
    0.47
    artz
    0.46
    жити
    0.46
     هزینه
    0.45
     artistas
    0.45
     Aarti
    0.45
    )、
    0.44
    Activations Density 0.000%

    No Known Activations