© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10538
    Prev
    Next
    INDEX
    Explanations

    product of

    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
     dependable
    2.80
    𝑎
    2.80
    oksatta
    2.63
    𝕒
    2.57
    क्टूबर
    2.56
    𝑣
    2.55
    𝑙
    2.49
    𝑐
    2.48
    ly
    2.47
    sanity
    2.46
    POSITIVE LOGITS
    `
    2.92
    ی
    2.79
    ie
    2.58
    ek
    2.45
    RE
    2.36
     --
    2.27
    ´
    2.18
     ----
    2.14
    ის
    2.14
    yu
    2.10
    Activations Density 0.056%

    No Known Activations