© 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. 48948
    Prev
    Next
    INDEX
    Explanations

    processes, customizable, buffering

    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
    that
    0.60
    ind
    0.54
    IND
    0.50
    ORM
    0.47
     對
    0.46
     صارت
    0.45
    穩
    0.45
    orin
    0.45
    牽
    0.45
    States
    0.44
    POSITIVE LOGITS
     customizable
    0.49
     مسؤول
    0.45
     oído
    0.44
    στα
    0.44
    чис
    0.43
    angwa
    0.43
     bagian
    0.42
     हिस्सा
    0.40
    alea
    0.40
     incarcerated
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.