© 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. 169721
    Prev
    Next
    INDEX
    Explanations

    administrative personnel

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

    Not since wife Elara

    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
     C
    0.44
     spray
    0.40
     triple
    0.40
     lonely
    0.39
    arcs
    0.38
    及其
    0.38
    isola
    0.38
     http
    0.38
     그리고
    0.38
     M
    0.37
    POSITIVE LOGITS
     پیشنه
    0.55
     комите
    0.52
    bottomMargin
    0.52
     Accountants
    0.51
    িক্স
    0.51
     ファイル
    0.51
     ouv
    0.50
     الاجتماعي
    0.50
    क्चर
    0.50
     pequeños
    0.50
    Activations Density 0.000%

    No Known Activations