© 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. 235800
    Prev
    Next
    INDEX
    Explanations

    globally unique and specific purposes

    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
    יי
    0.51
    Appuntamento
    0.45
    ನ್ನ
    0.45
     lesión
    0.44
    ロ
    0.44
    ді
    0.44
    R
    0.42
     سی
    0.42
    яр
    0.42
    اسي
    0.41
    POSITIVE LOGITS
     Positioning
    0.52
     cere
    0.50
     Selecting
    0.50
     Patents
    0.48
     브랜드
    0.48
    amide
    0.47
    circledR
    0.47
     copying
    0.46
    ridges
    0.46
     peaking
    0.46
    Activations Density 0.001%

    No Known Activations