© 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. 13-GEMMASCOPE-2-RES-16K
    7. 772
    Prev
    Next
    INDEX
    Explanations

    Punctuation and separators

    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_13_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
     Γ
    2.54
     κα
    2.49
     Χ
    2.48
     Δ
    2.47
     tons
    2.45
     πολύ
    2.44
     哦
    2.43
     攵
    2.42
     也
    2.42
     ϕ
    2.41
    POSITIVE LOGITS
    _
    2.68
    __
    2.17
    вЂ
    2.14
    ism
    2.05
    alex
    2.04
    সঙ্ঘ
    2.03
    -
    2.01
    japanese
    1.95
    ibuya
    1.93
    pesar
    1.93
    Activations Density 1.272%

    No Known Activations