© 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. 201843
    Prev
    Next
    INDEX
    Explanations

    establishes important, unique face

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

    million Bit, million coins, {"key", {"name

    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
    エラー
    0.59
    ڎ
    0.59
    浜
    0.56
    マ
    0.54
    PPPP
    0.53
    ⤠
    0.53
    ಮಗೆ
    0.51
    ⬤
    0.50
    CCCCCCCC
    0.50
    ACK
    0.50
    POSITIVE LOGITS
     coop
    0.49
     painters
    0.49
    ato
    0.48
     poets
    0.48
     cuticle
    0.48
     condenser
    0.47
     heuristic
    0.46
     baffled
    0.46
     mysteries
    0.46
     armies
    0.45
    Activations Density 0.001%

    No Known Activations