© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12379
    Prev
    Next
    INDEX
    Explanations

    tags assignment

    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
    ت
    3.08
    estell
    2.87
    s
    2.83
    ตรฐาน
    2.68
    destructive
    2.61
    ுள்ளனர்
    2.48
    ographystyle
    2.45
    sá
    2.44
    esque
    2.42
     HINSTANCE
    2.41
    POSITIVE LOGITS
    wego
    2.66
    vin
    2.61
    ships
    2.56
    nic
    2.56
    𝕀
    2.54
    str
    2.53
    seb
    2.41
    lde
    2.41
    டன்
    2.41
    teau
    2.40
    Activations Density 0.012%

    No Known Activations