© 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. 14078
    Prev
    Next
    INDEX
    Explanations

    defaults to parameter values

    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
    ៊
    1.63
    溶液
    1.63
     resistors
    1.61
    ਸੀ
    1.61
     χρησιμοποι
    1.58
    奏
    1.56
     선생님
    1.54
    zend
    1.53
    ｆ
    1.53
    aroni
    1.51
    POSITIVE LOGITS
    Carousel
    1.69
    два
    1.69
     Snapshot
    1.68
     Midwestern
    1.65
     Inventory
    1.61
     Biodiversity
    1.57
     Greenhouse
    1.57
     Dashboard
    1.56
    Tourism
    1.55
     homecoming
    1.52
    Activations Density 0.077%

    No Known Activations