© 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. 244624
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    u
    0.61
    h
    0.54
    st
    0.53
    n
    0.51
    p
    0.51
    '
    0.47
    j
    0.47
    on
    0.47
    je
    0.47
    mee
    0.47
    POSITIVE LOGITS
     echar
    0.57
     গাছের
    0.52
     cát
    0.51
    蛏
    0.51
     忄
    0.50
     interdit
    0.49
     agrup
    0.49
     seguimos
    0.48
    윰
    0.48
     możli
    0.47
    Activations Density 0.000%

    No Known Activations