© 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. 208177
    Prev
    Next
    INDEX
    Explanations

    leading companiesimportant Italianno contactInstant noodlesdifferent view

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

    direct result, volumes, manipulation, selection

    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
    ’
    0.47
    front
    0.46
     많
    0.44
     Type
    0.44
     homogeneity
    0.43
    available
    0.42
    political
    0.42
     polycarbonate
    0.42
     depletion
    0.42
    黐
    0.41
    POSITIVE LOGITS
    iça
    0.51
     gerente
    0.51
    Вели
    0.50
     descenso
    0.47
     Mancini
    0.46
     jusqu
    0.46
    χος
    0.46
     heures
    0.46
     fråga
    0.46
    ева
    0.44
    Activations Density 0.001%

    No Known Activations