© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9689
    Prev
    Next
    INDEX
    Explanations

    key improvements explanations

    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_9_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
     ‘‘
    1.14
     也
    1.07
     Ambul
    1.06
     都
    1.05
     (
    1.04
     πάντα
    1.03
     happily
    1.00
     refrain
    1.00
     ''
    0.98
     Midtown
    0.97
    POSITIVE LOGITS
    ы
    1.39
    ⺀
    1.32
    これにより
    1.26
    ///
    1.25
    ഓം
    1.23
    Во
    1.20
    /**
    1.15
    ärm
    1.12
    tan
    1.11
    ffmpeg
    1.11
    Activations Density 0.117%

    No Known Activations