© 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. 41-GEMMASCOPE-2-RES-262K
    7. 34994
    Prev
    Next
    INDEX
    Explanations

    numbers and chess notation

    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_all/layer_41_width_262k_l0_big
    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
     худ
    0.38
    anshi
    0.37
     discouraged
    0.34
     Lush
    0.33
     terrib
    0.33
     f
    0.32
     terrible
    0.32
    concepto
    0.32
    ouveau
    0.32
    th
    0.31
    POSITIVE LOGITS
    erView
    0.39
     drawable
    0.38
    脘
    0.38
     CYAN
    0.38
    ृत
    0.37
    განიზ
    0.37
    ಕೆಯ
    0.37
     rama
    0.35
    lockSeconds
    0.34
    মোহন
    0.33
    Activations Density 0.003%

    No Known Activations