© 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. 17-GEMMASCOPE-2-RES-16K
    7. 6
    Prev
    Next
    INDEX
    Explanations

    JSON and code syntax

    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_17_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
    сила
    0.65
    ?$
    0.63
    сил
    0.61
    влено
    0.61
    i
    0.58
    isempty
    0.57
    oren
    0.56
    குதி
    0.55
     deb
    0.54
    各自
    0.54
    POSITIVE LOGITS
    <unused0>
    0.90
     चव्हाण
    0.89
     দীননাথ
    0.86
     بالإضافة
    0.85
    、「
    0.84
    崎
    0.83
     notamment
    0.83
    ッピング
    0.83
     fundación
    0.83
     पाण्डे
    0.82
    Activations Density 0.017%

    No Known Activations