© 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. 94958
    Prev
    Next
    INDEX
    Explanations

    employment, positions, or roles

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

    structure and options

    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
    les
    0.52
    na
    0.52
    of
    0.51
    os
    0.49
    je
    0.46
    t
    0.45
    يت
    0.45
    j
    0.45
    el
    0.45
    re
    0.45
    POSITIVE LOGITS
    రంగ
    0.53
     парламента
    0.51
    ธุรก
    0.50
     контроль
    0.50
    тур
    0.49
    ሚያ
    0.49
     ပြော
    0.48
     закры
    0.48
    त्याने
    0.48
     первич
    0.48
    Activations Density 0.000%

    No Known Activations