© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14554
    Prev
    Next
    INDEX
    Explanations

    paid to provide

    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_7_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
    竴
    2.68
    ່ມ
    2.60
    ින්
    2.57
     قدر
    2.56
    분의
    2.48
    ቂያ
    2.46
    輳
    2.44
     परख
    2.40
    ]}\
    2.39
    BackPressed
    2.39
    POSITIVE LOGITS
    yki
    3.56
    uig
    2.93
    y
    2.88
    iou
    2.84
    eek
    2.77
    ochond
    2.48
    e
    2.48
    u
    2.46
    uet
    2.43
    یی
    2.42
    Activations Density 0.011%

    No Known Activations