© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2234
    Prev
    Next
    INDEX
    Explanations

    Jokes and jubilees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_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
    in
    2.31
    a
    1.48
    1
    1.34
    innt
    1.31
    play
    1.13
    5
    1.13
     can
    1.09
    hold
    1.09
    2
    1.09
    board
    1.06
    POSITIVE LOGITS
    м
    1.90
    م
    1.90
    ம்
    1.72
    ل
    1.67
    ة
    1.63
    મ
    1.62
    ী
    1.59
    ب
    1.55
    ك
    1.54
    س
    1.49
    Activations Density 0.444%

    No Known Activations