© 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-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1892
    Prev
    Next
    INDEX
    Explanations

    Gemma and Datalog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    2.17
    o
    2.02
    e
    1.82
    r
    1.81
    ر
    1.81
    u
    1.79
    a
    1.78
    in
    1.71
    et
    1.70
    া
    1.68
    POSITIVE LOGITS
    𝘴
    1.26
    정책
    1.22
    ERIC
    1.21
    Ü
    1.21
    İ
    1.20
    ilor
    1.17
    
    1.16
    antenna
    1.14
    𝘰
    1.14
    adas
    1.14
    Activations Density 1.248%

    No Known Activations