© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12097
    Prev
    Next
    INDEX
    Explanations

    book titles

    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_40_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
    <unused481>
    0.32
    ّل
    0.30
     Każ
    0.30
    <unused1975>
    0.30
     fasse
    0.30
     proporcion
    0.29
    <unused1012>
    0.29
     celui
    0.29
     سازمان
    0.29
    <unused108>
    0.29
    POSITIVE LOGITS
     typology
    0.46
     Handbook
    0.40
     handbook
    0.38
     monograph
    0.38
    Handbook
    0.38
     typical
    0.37
     interpretation
    0.35
     monographs
    0.35
     practical
    0.34
     cookbook
    0.34
    Activations Density 0.000%

    No Known Activations