© 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. 180603
    Prev
    Next
    INDEX
    Explanations

    lists containing nouns

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

    context, value, data, segments, Run Date

    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
    s
    0.67
    <0x0D>
    0.55
    ly
    0.55
    hip
    0.54
    log
    0.53
    l
    0.53
    nie
    0.50
    éon
    0.49
     conco
    0.49
    ners
    0.49
    POSITIVE LOGITS
    琰
    0.49
    なくて
    0.48
    تما
    0.46
     jukebox
    0.44
     করিলেন
    0.44
    احمد
    0.44
     Gesture
    0.43
    ابر
    0.43
     probabilities
    0.43
    мін
    0.43
    Activations Density 0.001%

    No Known Activations