© 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. 123986
    Prev
    Next
    INDEX
    Explanations

    instructional phrases

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

    images and photos

    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
    绸
    0.48
     emoc
    0.47
    விடும்
    0.47
     hci
    0.46
     Raul
    0.46
     قاس
    0.45
     đổ
    0.44
     cajas
    0.44
     culturales
    0.44
    apiRequest
    0.44
    POSITIVE LOGITS
    3
    0.55
    4
    0.55
     espèce
    0.47
    史上
    0.46
    Features
    0.46
     principle
    0.46
    ご覧
    0.46
     फार्मा
    0.46
     enhancing
    0.46
    非常に
    0.46
    Activations Density 0.001%

    No Known Activations