© 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. 1732
    Prev
    Next
    INDEX
    Explanations

    clear statements or strong evaluations

    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
    த்தம்
    0.70
    ंस
    0.65
     speakers
    0.64
    ="__
    0.64
     directions
    0.62
     lao
    0.62
     results
    0.61
    িস
    0.61
     small
    0.61
     موز
    0.61
    POSITIVE LOGITS
    ⅔
    1.14
     majority
    1.12
     ninety
    1.10
     ৯০
    1.05
    ９
    1.04
     çoğu
    1.03
    majority
    1.02
    一半
    1.01
     majorité
    1.00
     Ninety
    1.00
    Activations Density 0.318%

    No Known Activations