© 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. 219245
    Prev
    Next
    INDEX
    Explanations

    a concluding word or punctuation

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

    flaky crust

    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
    적
    0.46
     introns
    0.44
    물
    0.42
     neoplasms
    0.42
    이자
    0.42
    널
    0.41
    éticos
    0.41
    활
    0.40
    مان
    0.40
     golongan
    0.40
    POSITIVE LOGITS
     Ohio
    0.56
     by
    0.53
     New
    0.53
    with
    0.53
     Maple
    0.53
     with
    0.52
     gives
    0.52
     Says
    0.52
    ko
    0.51
     มือ
    0.51
    Activations Density 0.000%

    No Known Activations