© 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. 159
    Prev
    Next
    INDEX
    Explanations

    eager thanks help confidence

    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
     Gazetteer
    1.26
    ತ್ತ
    1.26
    ýt
    1.19
     BY
    1.16
    ાઇલ
    1.16
    内の
    1.12
     `=`,
    1.09
    ικού
    1.09
    亢
    1.07
    ็ว
    1.07
    POSITIVE LOGITS
    FULLY
    1.63
    śmy
    1.60
    lul
    1.52
    тво
    1.45
     realisation
    1.42
    สดง
    1.40
    etek
    1.39
    fulfillment
    1.38
     серд
    1.38
     نصی
    1.38
    Activations Density 2.965%

    No Known Activations