© 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. 2238
    Prev
    Next
    INDEX
    Explanations

    AI tools and services

    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
    ly
    0.99
    '
    0.97
    ’
    0.92
     aka
    0.91
    ,
    0.90
    an
    0.90
     Captain
    0.89
     acclaimed
    0.88
    os
    0.88
    -
    0.87
    POSITIVE LOGITS
    <unused1585>
    1.30
    ⺆
    1.22
    밂
    1.22
    <unused1182>
    1.22
    퇸
    1.20
    popupIsOpen
    1.20
    <unused1492>
    1.19
    <unused1489>
    1.19
    쳏
    1.18
    bindingFields
    1.18
    Activations Density 0.287%

    No Known Activations