© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9029
    Prev
    Next
    INDEX
    Explanations

    application startup actions

    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
    ชาติ
    0.97
     Peugeot
    0.93
     ши
    0.90
    ができる
    0.89
    roud
    0.88
    บาย
    0.88
    </h2>
    0.86
     SDG
    0.86
    e
    0.85
     fabric
    0.84
    POSITIVE LOGITS
    آور
    1.47
    电子邮件
    1.47
    ºC
    1.43
     appetizing
    1.42
    picklist
    1.41
    黯
    1.32
    ówka
    1.31
     vinegar
    1.31
    ੧
    1.30
     전혀
    1.30
    Activations Density 0.000%

    No Known Activations