© 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. 367
    Prev
    Next
    INDEX
    Explanations

    foreign languages and scripts

    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
    owaniem
    0.57
     tone
    0.54
     하나
    0.53
     მიმოწერა
    0.53
     anything
    0.52
     nothing
    0.50
    alam
    0.49
    ុ
    0.49
     너
    0.49
    峀
    0.49
    POSITIVE LOGITS
    Becoming
    0.74
    Bitter
    0.71
    Enjoy
    0.70
    Facing
    0.69
    Dreams
    0.67
    Racing
    0.65
    Header
    0.64
    Myst
    0.64
    Despite
    0.64
    Choosing
    0.64
    Activations Density 1.018%

    No Known Activations