© 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. 52317
    Prev
    Next
    INDEX
    Explanations

    ways into the things

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

    crucial explanation

    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
    an
    0.52
    AS
    0.50
     WEEK
    0.48
    i
    0.46
    写真は
    0.46
    ا
    0.45
    baixo
    0.45
    ۳
    0.45
     gioi
    0.45
    ISTICS
    0.44
    POSITIVE LOGITS
     Trophy
    0.49
    ಿಸಿಕೊಳ್ಳ
    0.49
    ínio
    0.48
     Posterior
    0.46
     diffeomorphism
    0.46
     Gletscher
    0.46
    ിക്കും
    0.46
     Trop
    0.44
     ordained
    0.44
     Maitland
    0.44
    Activations Density 0.000%

    No Known Activations