© 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. 8596
    Prev
    Next
    INDEX
    Explanations

    words formed by common prefixes

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

    decisions, domains, services, organizations, intimacy, intj

    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
    ąp
    0.29
    𝗕
    0.29
    śmy
    0.28
    𐰇
    0.28
    ブラ
    0.27
    ня
    0.27
    वाँ
    0.26
    fragt
    0.26
    verifica
    0.26
    してみてください
    0.26
    POSITIVE LOGITS
    ication
    0.28
    ulators
    0.28
     personnels
    0.28
     intelectual
    0.27
     Officials
    0.26
    ké
    0.26
    0
    0.25
     Offices
    0.25
     Mileage
    0.25
     of
    0.25
    Activations Density 0.155%

    No Known Activations