© 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. 31-GEMMASCOPE-2-RES-262K
    7. 90997
    Prev
    Next
    INDEX
    Explanations

    str(

    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_31_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
    觀
    0.49
    ية
    0.48
    ا
    0.48
    較
    0.48
    </em>
    0.46
    ማ
    0.45
    мо
    0.45
    is
    0.44
    赤
    0.44
     Spitz
    0.43
    POSITIVE LOGITS
     یقینی
    0.47
    tuvo
    0.46
     khóa
    0.46
     fdata
    0.45
     تاریخی
    0.45
     rhetorical
    0.45
     varicose
    0.44
     tört
    0.43
    timedelta
    0.42
    rochemical
    0.42
    Activations Density 0.015%

    No Known Activations