© 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. 24321
    Prev
    Next
    INDEX
    Explanations

    CAG repeat expansion

    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
    颱
    0.48
     jockey
    0.40
    ُول
    0.39
    振動
    0.39
    體
    0.39
     reels
    0.38
     inadmissible
    0.38
     pins
    0.37
     szok
    0.37
     極
    0.37
    POSITIVE LOGITS
     shapes
    0.48
     Shapes
    0.45
    Genome
    0.42
     transcript
    0.40
     transcriptional
    0.39
    写入
    0.39
     bakar
    0.39
    shapes
    0.39
     Analytics
    0.38
    GED
    0.38
    Activations Density 0.000%

    No Known Activations