© 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. 12006
    Prev
    Next
    INDEX
    Explanations

    compound exercises

    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
    có
    2.67
    c
    2.53
    ko
    2.48
    なく
    2.46
    ty
    2.41
    x
    2.36
    पोज
    2.30
    pair
    2.25
    anonymous
    2.22
    ther
    2.22
    POSITIVE LOGITS
    ချုပ်
    3.11
     nascetur
    2.84
    ed
    2.78
    icillin
    2.75
     spongy
    2.71
    varchar
    2.65
    ie
    2.63
    VARCHAR
    2.56
    ebilirsiniz
    2.56
    禺
    2.53
    Activations Density 0.006%

    No Known Activations