© 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. 14190
    Prev
    Next
    INDEX
    Explanations

    pointers and criteria

    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
    ripción
    2.73
    gaben
    2.69
    sá
    2.60
    aient
    2.60
    စွာ
    2.56
    턴
    2.51
    િજા
    2.49
    iduría
    2.48
    ाना
    2.46
    تری
    2.44
    POSITIVE LOGITS
    ार्क
    2.52
    적으로
    2.44
    ่
    2.27
    DUCT
    2.25
    atic
    2.20
    LENGTH
    2.19
    ">>
    2.19
    unch
    2.19
    დ
    2.16
    no
    2.12
    Activations Density 0.009%

    No Known Activations