© 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. 128192
    Prev
    Next
    INDEX
    Explanations

    herbal medicine

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

    adapted, questionnaires

    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
    Anche
    0.49
    F
    0.47
    ologica
    0.46
    알
    0.46
    Liv
    0.45
    babel
    0.45
    Lot
    0.45
    𖤐
    0.45
    Daily
    0.44
    präsident
    0.44
    POSITIVE LOGITS
     hObject
    0.52
     Tokugawa
    0.52
     Wii
    0.51
     Wife
    0.50
    ِب
    0.50
     भूमि
    0.49
     GameObject
    0.48
     FormGroup
    0.46
     Benutzer
    0.46
     Đối
    0.46
    Activations Density 0.000%

    No Known Activations