© 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. 12496
    Prev
    Next
    INDEX
    Explanations

    sans-serif

    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
    （
    1.63
     විසින්
    1.58
     provides
    1.57
     （
    1.52
    における
    1.50
     jako
    1.46
    法施行令
    1.46
    คณะ
    1.46
    에서는
    1.45
     for
    1.44
    POSITIVE LOGITS
    𝐦
    1.74
    igt
    1.64
    iti
    1.61
    tono
    1.54
    𝐩
    1.54
    𝐯
    1.53
    𝐥
    1.53
    𝗺
    1.53
     दूरी
    1.53
    keypress
    1.51
    Activations Density 0.034%

    No Known Activations