© 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. 12035
    Prev
    Next
    INDEX
    Explanations

    dive into

    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
    шую
    3.10
    ück
    2.83
    სი
    2.81
    ું
    2.76
    ︎
    2.71
     scriptlevel
    2.68
    〟
    2.67
    ों
    2.67
    𝖙
    2.66
    ʖ
    2.66
    POSITIVE LOGITS
    e
    4.87
    a
    4.39
    y
    3.78
    o
    3.69
    ו
    3.64
    는
    3.52
    i
    3.43
    ه
    3.38
    יים
    3.31
    া
    3.21
    Activations Density 0.039%

    No Known Activations