© 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. 14422
    Prev
    Next
    INDEX
    Explanations

    matrix definition starts

    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
    ╕
    2.76
    чать
    2.75
    ⩾
    2.74
    శ
    2.50
    軸
    2.46
    <bos>
    2.43
    ánd
    2.43
     financière
    2.42
    ковы
    2.42
    ☓
    2.40
    POSITIVE LOGITS
    getView
    2.31
    ଁ
    2.27
     ir
    2.16
    dur
    2.15
    श्किल
    2.10
    dy
    2.09
    vek
    2.07
    sent
    2.05
    lamak
    2.00
    臾
    1.96
    Activations Density 0.010%

    No Known Activations