© 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. 226277
    Prev
    Next
    INDEX
    Explanations

    services and conditions

    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
     партия
    0.53
     corri
    0.53
    oul
    0.51
    arovski
    0.50
    襷
    0.50
    ’
    0.50
     яй
    0.50
    anjing
    0.49
    apatillas
    0.49
    archiw
    0.49
    POSITIVE LOGITS
     Pian
    0.48
    正是
    0.47
     Barton
    0.47
    关键
    0.46
    常
    0.46
    λη
    0.44
    차
    0.44
    關鍵
    0.43
     Orta
    0.43
     LaSalle
    0.43
    Activations Density 0.000%

    No Known Activations