© 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. 246180
    Prev
    Next
    INDEX
    Explanations

    lists, contents, or 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
    QTTR
    0.50
    疹
    0.48
    密切
    0.47
    vamente
    0.47
     చిన్న
    0.47
     ಹುಡು
    0.46
    爾
    0.46
    ocèle
    0.45
    ўні
    0.45
    ární
    0.45
    POSITIVE LOGITS
    ’
    0.63
    Robot
    0.54
    Az
    0.52
    น
    0.52
    Cost
    0.51
    '
    0.51
    Size
    0.47
    Content
    0.47
    Digital
    0.47
    List
    0.47
    Activations Density 0.000%

    No Known Activations