© 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. 14430
    Prev
    Next
    INDEX
    Explanations

    theme modeling

    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
    en
    2.86
    u
    2.80
    ೇಶ
    2.45
    enal
    2.39
    дного
    2.38
    тира
    2.31
    issu
    2.28
    perd
    2.24
    wss
    2.22
    во
    2.21
    POSITIVE LOGITS
    竴
    3.02
     Bxh
    2.75
    ្យ
    2.64
    sí
    2.61
    ურთ
    2.57
     `'
    2.56
    rocyte
    2.56
    ႇ
    2.55
     hObject
    2.54
     garam
    2.50
    Activations Density 0.000%

    No Known Activations