© 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. 2324
    Prev
    Next
    INDEX
    Explanations

    cook until fragrant

    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
     extrémité
    0.43
    ="#!"
    0.41
     `<=`
    0.35
     subchapter
    0.34
    coll
    0.33
    objClass
    0.33
     Cllr
    0.33
     үч
    0.32
     चिंता
    0.32
     ThemeData
    0.32
    POSITIVE LOGITS
     References
    0.38
    References
    0.35
     Gambar
    0.35
     innoc
    0.35
    透
    0.34
     references
    0.33
    pyrrolo
    0.32
    Ｓ
    0.32
     REFERENCES
    0.32
     ссылки
    0.32
    Activations Density 0.002%

    No Known Activations