© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 12798
    Prev
    Next
    INDEX
    Explanations

    code comments explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
     ہے۔
    0.88
    .}~\
    0.87
    \":
    0.82
     функциони
    0.80
    :**
    0.78
     следующих
    0.77
    的历史
    0.77
     самостоятельно
    0.75
    собенности
    0.75
    :");
    0.74
    POSITIVE LOGITS
     noqa
    1.24
     <--
    1.13
    这里
    1.04
     注意
    0.98
     这里
    0.96
     Added
    0.95
    或者
    0.91
     或者
    0.90
     тобто
    0.89
    这是
    0.89
    Activations Density 0.240%

    No Known Activations