© 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. 9240
    Prev
    Next
    INDEX
    Explanations

    fall and subsequent terms

    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
    angular
    2.53
    a
    2.40
    تف
    2.22
    aio
    2.22
    aul
    2.17
    /**',
    2.15
    िज्या
    2.14
    emph
    2.13
    ał
    2.08
    ר
    2.08
    POSITIVE LOGITS
    .”[
    2.05
    [/
    1.92
    --“
    1.88
    落
    1.87
    “[
    1.85
    은
    1.81
    ();}
    1.79
    np
    1.77
    𝐢
    1.77
    ;}
    1.76
    Activations Density 0.262%

    No Known Activations