© 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. 45
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    ListenAndServe
    1.57
    setPointSize
    1.57
    retry
    1.51
    폰
    1.49
    ្ស
    1.49
    rap
    1.47
     불구
    1.47
    loadNpmTasks
    1.42
     getan
    1.40
    createServer
    1.34
    POSITIVE LOGITS
    狈
    1.75
    狽
    1.71
    ódulo
    1.71
    م
    1.68
    ્ઞ
    1.65
    বীন্দ্র
    1.55
    erent
    1.55
    ्ड
    1.52
    ⁰
    1.49
     tratti
    1.49
    Activations Density 0.637%

    No Known Activations