© 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. 1759
    Prev
    Next
    INDEX
    Explanations

    risk categories and examples

    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
    API
    0.67
    :*
    0.67
    APH
    0.63
     rocking
    0.63
     effortlessly
    0.63
    STRA
    0.63
    PB
    0.62
    Juni
    0.62
     perfectly
    0.61
    :$
    0.60
    POSITIVE LOGITS
     vagy
    0.77
     uống
    0.76
    වුන්
    0.72
     hoặc
    0.68
     consequat
    0.66
    localObject
    0.66
     amelyet
    0.66
     krwi
    0.65
     lésions
    0.65
     típ
    0.65
    Activations Density 0.002%

    No Known Activations