© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1239
    Prev
    Next
    INDEX
    Explanations

    level/rank/tier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    あっ
    1.61
     rédu
    1.54
    ંદ્ર
    1.54
    ảm
    1.46
    мень
    1.41
    uduk
    1.41
     réduit
    1.40
    沧
    1.38
    stopwords
    1.38
     aliv
    1.37
    POSITIVE LOGITS
     올라
    2.06
    stakes
    1.95
     higher
    1.80
    GRADE
    1.79
     lên
    1.74
    ulence
    1.74
     hierarchical
    1.72
     percentile
    1.69
     tope
    1.68
    ⤴
    1.67
    Activations Density 0.943%

    No Known Activations