© 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. 2174
    Prev
    Next
    INDEX
    Explanations

    highlighting specific conditions

    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
    ös
    2.95
    𝕡
    2.77
    ⁡
    2.61
    ృష్టి
    2.60
    鸯
    2.50
    ριν
    2.47
    ŷ
    2.43
    ત
    2.37
    തന്ത്ര
    2.37
    íp
    2.34
    POSITIVE LOGITS
    en
    3.73
    e
    3.66
    ا
    3.50
    y
    3.43
    י
    3.39
    enje
    3.37
    eal
    3.28
    る
    3.26
    afe
    3.25
    יים
    3.20
    Activations Density 0.228%

    No Known Activations