© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131714
    Prev
    Next
    INDEX
    Explanations

    city, Grade, opinion, statements

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

    list items or definitions

    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
     pregnancies
    0.59
     गर्भ
    0.57
     ピ
    0.54
     dernier
    0.54
     nn
    0.53
     capacité
    0.53
     vår
    0.53
     neuropathy
    0.53
     proteinuria
    0.53
     lahir
    0.52
    POSITIVE LOGITS
    ना
    0.48
    나
    0.47
    clas
    0.46
    a
    0.43
    匡
    0.43
    快
    0.42
    inais
    0.42
    構
    0.42
    Į
    0.42
    做
    0.41
    Activations Density 0.000%

    No Known Activations