© 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. 10778
    Prev
    Next
    INDEX
    Explanations

    essential weekly only

    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
    ELLOW
    1.27
     Lever
    1.26
     aka
    1.24
     PAS
    1.20
     quà
    1.19
     солне
    1.19
    <unused2187>
    1.17
     Ballard
    1.17
     Didn
    1.17
     zy
    1.17
    POSITIVE LOGITS
    其他
    1.17
    地点
    1.16
    치의
    1.11
    icherheit
    1.09
    査
    1.05
    General
    1.03
    other
    1.03
    別の
    1.03
     perbedaan
    1.02
    汇总
    1.01
    Activations Density 0.000%

    No Known Activations