© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191316
    Prev
    Next
    INDEX
    Explanations

    academic thesis or masters

    np_acts-logits-general · gemini-2.5-flash-lite

    reptilian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    你有
    0.47
     bed
    0.47
    去年
    0.47
    今年
    0.46
    2
    0.46
     unlock
    0.45
     accion
    0.44
    。”
    0.44
     but
    0.43
    الس
    0.43
    POSITIVE LOGITS
    OLYBD
    0.46
     कार्यकाल
    0.45
    avkh
    0.45
    enov
    0.45
    দায়িক
    0.44
     biographical
    0.44
     COMMERCIAL
    0.44
     biographer
    0.44
     প্রস্তাব
    0.43
    鬻
    0.42
    Activations Density 0.000%

    No Known Activations