© 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. 111699
    Prev
    Next
    INDEX
    Explanations

    value or characteristic

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

    relationships and associations

    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
     provoking
    0.53
    かれた
    0.52
    했
    0.48
    机遇
    0.48
    ومین
    0.48
    क्ती
    0.48
    मित्व
    0.47
    ação
    0.47
    ியோ
    0.47
    úscula
    0.47
    POSITIVE LOGITS
    4
    0.58
    Straight
    0.49
    %
    0.49
    ES
    0.47
    sum
    0.46
    Database
    0.46
    6
    0.46
    Endpoint
    0.46
    5
    0.46
    AP
    0.45
    Activations Density 0.000%

    No Known Activations