© 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. 83214
    Prev
    Next
    INDEX
    Explanations

    collections, quantities, and counts

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

    following certain words with descriptions

    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
    考え
    0.56
    ら
    0.51
     conhe
    0.45
     образом
    0.45
    үү
    0.45
     Proctor
    0.44
     tanah
    0.44
    ъ
    0.44
    жную
    0.43
     négl
    0.43
    POSITIVE LOGITS
    rating
    0.49
    airport
    0.48
    Laptop
    0.47
    frying
    0.47
    closed
    0.47
    wallet
    0.46
    Phone
    0.46
    heart
    0.46
    quoted
    0.46
    al
    0.46
    Activations Density 0.000%

    No Known Activations