© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14387
    Prev
    Next
    INDEX
    Explanations

    drawing on screen

    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_7_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
    `${
    2.94
    וש
    2.72
    venor
    2.57
    `(
    2.49
    ⁢</
    2.47
    `<
    2.45
    getRandom
    2.42
    resc
    2.40
    $~
    2.36
    irre
    2.35
    POSITIVE LOGITS
    istä
    2.41
    یکیشن
    2.38
     stali
    2.37
    𝙣
    2.35
     gacchati
    2.33
    ুপ্ত
    2.30
    istration
    2.25
     bhavati
    2.24
    itti
    2.22
    isierung
    2.21
    Activations Density 0.002%

    No Known Activations