© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8999
    Prev
    Next
    INDEX
    Explanations

    rain lashes, streaks, hammered

    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
    িক
    3.00
    ും
    2.82
    𝘢
    2.65
    я
    2.63
    㐄
    2.60
     gerade
    2.60
     covariate
    2.55
     sway
    2.53
    śmy
    2.52
    ع
    2.49
    POSITIVE LOGITS
    ouchers
    2.65
     Bxa
    2.57
    घरों
    2.51
    runoff
    2.51
    forestation
    2.49
     чином
    2.44
    ுங்கள்
    2.42
     kenapa
    2.42
    骈
    2.36
    BOW
    2.35
    Activations Density 0.030%

    No Known Activations