© 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. 236420
    Prev
    Next
    INDEX
    Explanations

    accessory

    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
    lerim
    0.50
    진다
    0.49
    점에
    0.48
    기에
    0.47
     REACTORS
    0.46
     CHO
    0.46
    덴
    0.44
     ставка
    0.44
    azier
    0.44
     CORPER
    0.43
    POSITIVE LOGITS
     Accessory
    0.48
    త
    0.47
    导
    0.47
     accessory
    0.44
    কা
    0.44
    ખ
    0.43
    極
    0.43
     Severe
    0.43
    sm
    0.43
    左右
    0.43
    Activations Density 0.000%

    No Known Activations