© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 18954
    Prev
    Next
    INDEX
    Explanations

    `settings` or `options`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulas
    0.75
    なかなか
    0.72
    ларын
    0.69
    фи
    0.69
     mathvariant
    0.68
    もので
    0.67
    骊
    0.65
    +
    0.65
    alahan
    0.64
    ль
    0.64
    POSITIVE LOGITS
     tram
    0.89
    ﴾
    0.86
     oude
    0.85
     trumpet
    0.83
     хле
    0.83
     backed
    0.82
     js
    0.82
     sols
    0.82
     カップ
    0.81
     gór
    0.81
    Activations Density 0.000%

    No Known Activations