© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 49729
    Prev
    Next
    INDEX
    Explanations

    database backups

    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_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
     Blueberry
    0.45
    ዝ
    0.42
    keyboard
    0.42
    FIELD
    0.39
     Tjiwarl
    0.38
    विज्ञान
    0.38
     Discover
    0.38
    토
    0.37
     scalar
    0.37
     Lobster
    0.37
    POSITIVE LOGITS
    教堂
    0.42
    Profil
    0.39
    ือด
    0.37
    OIL
    0.37
    OpenGL
    0.36
    要注意
    0.36
    不必
    0.36
     edn
    0.36
    uska
    0.36
    ً
    0.36
    Activations Density 0.001%

    No Known Activations