© 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. 104783
    Prev
    Next
    INDEX
    Explanations

    select a keyword type

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

    concepts

    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
     カラ
    0.54
     どう
    0.47
     電話
    0.46
    貶
    0.46
    bestroute
    0.46
     ಲಕ್ಷ
    0.45
     الله
    0.45
    តិ
    0.45
     同じ
    0.45
    plante
    0.45
    POSITIVE LOGITS
     Aut
    0.52
    T
    0.51
    IN
    0.51
     Motor
    0.51
    ด้าน
    0.49
     National
    0.48
     Forestry
    0.48
     League
    0.47
     Forest
    0.47
    h
    0.46
    Activations Density 0.001%

    No Known Activations