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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13771
    Prev
    Next
    INDEX
    Explanations

    useEffect hook

    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
    에
    2.72
    वानगी
    2.53
    に
    2.52
    ის
    2.49
    weixin
    2.41
    relating
    2.35
    stricken
    2.34
    authenticate
    2.29
     τρόπο
    2.29
    ro
    2.24
    POSITIVE LOGITS
    tien
    3.52
    tion
    3.21
    t
    3.19
    tan
    2.88
    tol
    2.85
    $^{
    2.77
    𝘦
    2.74
    men
    2.74
    𝐡
    2.70
    서
    2.69
    Activations Density 0.001%

    No Known Activations