© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15520
    Prev
    Next
    INDEX
    Explanations

    command line practice

    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_16k_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
    тические
    1.33
     تړ
    1.32
     همچنین
    1.32
    ísticas
    1.30
    тический
    1.26
     речо
    1.23
    Other
    1.22
    є
    1.22
     otras
    1.22
    žas
    1.20
    POSITIVE LOGITS
    深深
    1.11
     mãi
    1.00
    直到
    0.93
    听
    0.90
    没人
    0.87
    再说
    0.86
     WIND
    0.84
    不幸
    0.83
    党
    0.82
    র্ন
    0.81
    Activations Density 0.030%

    No Known Activations