© 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. 14087
    Prev
    Next
    INDEX
    Explanations

    Western tradition, cultures, countries

    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
    ろん
    2.80
    া
    2.64
    いない
    2.63
    ிருஷ்
    2.62
    REZ
    2.55
    ्रीय
    2.55
    ोली
    2.50
    كون
    2.43
    powder
    2.41
    ee
    2.38
    POSITIVE LOGITS
    র
    3.11
    t
    3.02
    ર
    2.91
    م
    2.86
    tif
    2.78
    ने
    2.64
    ์
    2.61
    ر
    2.61
    ு
    2.53
    дзе
    2.50
    Activations Density 0.009%

    No Known Activations