© 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. 170378
    Prev
    Next
    INDEX
    Explanations

    submit, consent, date, customer, form

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

    complicate control or navigation

    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
     imagination
    0.51
     wybrać
    0.46
     yapıl
    0.44
     bitOp
    0.44
    <unused1051>
    0.44
     사람들이
    0.44
     보여
    0.43
     ঘটনায়
    0.43
     Союза
    0.43
     topology
    0.42
    POSITIVE LOGITS
     KA
    0.51
     KE
    0.50
     Fuller
    0.49
     Airline
    0.48
     Dive
    0.47
     Skipping
    0.47
     Allgeme
    0.46
    ६
    0.46
     Dew
    0.46
     Agua
    0.45
    Activations Density 0.000%

    No Known Activations