© 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. 81541
    Prev
    Next
    INDEX
    Explanations

    local payment

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

    Foreign words and code syntax

    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
     intensification
    0.44
    dicts
    0.44
    ulently
    0.41
    lipid
    0.40
    interpolate
    0.40
    †
    0.40
    dense
    0.39
    akova
    0.39
    ７
    0.39
    (\{
    0.39
    POSITIVE LOGITS
     stadion
    0.52
    टीवी
    0.50
     फ्रेम
    0.48
    抔
    0.45
     bentuk
    0.44
     sekal
    0.44
     zespół
    0.44
     चैनल
    0.43
     disque
    0.43
     Seung
    0.43
    Activations Density 0.001%

    No Known Activations