© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    Infection risk

    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
    课
    1.83
    printed
    1.82
    graphic
    1.82
    teenth
    1.78
    ند
    1.76
    strings
    1.75
     trained
    1.75
    dep
    1.73
    қы
    1.71
     interloc
    1.71
    POSITIVE LOGITS
    า
    2.81
    sina
    2.65
    ግዳ
    2.63
    szer
    2.58
    고
    2.57
    тном
    2.42
     laterales
    2.42
    าค
    2.42
    ಯಲ್ಲಿ
    2.37
    ી
    2.35
    Activations Density 0.024%

    No Known Activations