© 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. 94580
    Prev
    Next
    INDEX
    Explanations

    places or locations

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

    names and specific entities

    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
    𝚗
    0.56
    力を
    0.51
    力が
    0.50
    力
    0.50
     ventaja
    0.49
    力の
    0.48
     thrott
    0.48
     фи
    0.47
    ка
    0.46
    력
    0.46
    POSITIVE LOGITS
     Whitney
    0.48
     Elton
    0.47
    ceived
    0.47
     Valentino
    0.46
     Maraton
    0.46
    aratus
    0.46
     Maurizio
    0.46
     Waltz
    0.46
     Wedding
    0.45
     Ordinary
    0.45
    Activations Density 0.001%

    No Known Activations