© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 240452
    Prev
    Next
    INDEX
    Explanations

    block metric

    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
     收
    0.46
    hto
    0.46
     সত্ব
    0.43
    化
    0.41
    攒
    0.41
     未来
    0.41
     GPIO
    0.40
    ise
    0.39
     tiên
    0.39
     সীম
    0.39
    POSITIVE LOGITS
    ਾਰ
    0.55
    ਾਈ
    0.55
    엿
    0.54
    АТ
    0.50
    ಷ್ಯ
    0.50
    ಮ
    0.50
    тэ
    0.48
    РЕ
    0.48
    ]')
    0.47
    tempo
    0.47
    Activations Density 0.000%

    No Known Activations