© 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. 22-GEMMASCOPE-2-RES-16K
    7. 287
    Prev
    Next
    INDEX
    Explanations

    never, no

    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_22_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
    anthem
    0.90
    alias
    0.78
     Sah
    0.75
     nta
    0.75
    intas
    0.74
    int
    0.72
    acterium
    0.72
    N
    0.70
    tran
    0.69
     uga
    0.69
    POSITIVE LOGITS
     sought
    0.77
     lingered
    0.76
     رکھنا
    0.72
     insured
    0.72
     boasted
    0.71
     contended
    0.71
     clung
    0.71
     sported
    0.70
     wore
    0.68
     exhibited
    0.68
    Activations Density 0.494%

    No Known Activations