© 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. 2771
    Prev
    Next
    INDEX
    Explanations

    actual or real usage

    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
    ה
    1.73
    Pagination
    1.58
    ड्रन
    1.55
    余
    1.52
     dériv
    1.52
    𝙤
    1.48
    新增
    1.46
    旋
    1.46
    añas
    1.45
    ครัว
    1.45
    POSITIVE LOGITS
    keits
    1.70
    tions
    1.62
     estate
    1.60
    仡
    1.59
     অর্থে
    1.58
     '//
    1.54
    imately
    1.54
    geving
    1.53
    tio
    1.47
    acchati
    1.46
    Activations Density 0.780%

    No Known Activations