© 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-65K
    7. 55982
    Prev
    Next
    INDEX
    Explanations

    tikz latex code

    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
     ثلاثة
    0.43
    龕
    0.40
    )،
    0.39
    蛆
    0.36
    仨
    0.36
    textwidth
    0.36
    Delimiter
    0.36
    闿
    0.36
    Signing
    0.36
     livid
    0.36
    POSITIVE LOGITS
     Thousand
    0.41
     ஆயிரம்
    0.40
     true
    0.40
     TRUE
    0.40
     Tradu
    0.38
    ູ
    0.38
     suitcases
    0.37
     casos
    0.37
    clip
    0.36
    üsü
    0.36
    Activations Density 0.002%

    No Known Activations