© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15861
    Prev
    Next
    INDEX
    Explanations

    file operations or uploads

    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_13_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
    aft
    2.48
    ae
    2.33
     forg
    2.32
    or
    2.29
    ायचे
    2.27
    াজিক
    2.24
    ardust
    2.20
    限
    2.20
    恕
    2.15
    ی
    2.15
    POSITIVE LOGITS
    :///
    3.52
    рда
    3.01
    armonic
    2.98
    럿
    2.95
    lds
    2.93
    urgie
    2.93
    ThemeOverlay
    2.86
    osof
    2.85
    ້ອ
    2.65
    Houses
    2.60
    Activations Density 0.147%

    No Known Activations