© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213248
    Prev
    Next
    INDEX
    Explanations

    options, states, designed, Turkey, had, twist, enhance, Plus

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

    accessiblity, network, extraction

    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
    Negative Logits
     complaining
    0.55
    i
    0.54
    (
    0.54
    [_
    0.53
    e
    0.52
    ie
    0.51
    is
    0.50
     complaints
    0.50
    ail
    0.49
    ه
    0.49
    POSITIVE LOGITS
    nali
    0.50
     bringt
    0.48
    禳
    0.47
    <unused50>
    0.47
     führt
    0.47
    Acetoxy
    0.46
     nových
    0.46
    كره
    0.46
     nowego
    0.46
    ദ്ധതി
    0.46
    Activations Density 0.000%

    No Known Activations