© 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. 195448
    Prev
    Next
    INDEX
    Explanations

    mechanical engineer

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

    styling and modifications

    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
    5
    0.52
    '
    0.50
    asts
    0.48
     Yogi
    0.47
    `
    0.46
    ol
    0.46
    最好
    0.46
    ß
    0.46
     English
    0.45
    igate
    0.45
    POSITIVE LOGITS
    리
    0.56
     trabalhadores
    0.53
    mensaje
    0.52
     trabajadores
    0.51
     শ্রমিক
    0.50
    ツイ
    0.50
    冠軍
    0.50
    ків
    0.50
    針對
    0.50
     ಬೆಳ
    0.49
    Activations Density 0.000%

    No Known Activations