© 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. 10031
    Prev
    Next
    INDEX
    Explanations

    python self

    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
     微
    0.93
     സൂര്യ
    0.91
     ሁ
    0.90
    ่ม
    0.90
    吡
    0.88
    ў
    0.87
     சூரிய
    0.86
     दोपहर
    0.86
    微
    0.85
    usnya
    0.85
    POSITIVE LOGITS
    props
    1.37
     Props
    0.93
     المثل
    0.88
     props
    0.86
    kelly
    0.86
    comps
    0.85
     Cren
    0.81
    θο
    0.80
    xs
    0.78
    Props
    0.78
    Activations Density 0.008%

    No Known Activations