© 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. 146418
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

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

    strange or unusual wording

    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
    묵
    0.50
    ever
    0.47
    water
    0.46
    amed
    0.45
    found
    0.44
    $
    0.44
    bey
    0.44
    ümü
    0.44
    ic
    0.44
    ğim
    0.43
    POSITIVE LOGITS
     ارتفاع
    0.52
     администра
    0.49
    崠
    0.48
     Haemat
    0.45
    他说
    0.44
     лицен
    0.44
     pédagog
    0.44
    ือ
    0.43
    潞
    0.43
    棂
    0.43
    Activations Density 0.001%

    No Known Activations