© 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. 94332
    Prev
    Next
    INDEX
    Explanations

    peace, season, beach

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

    structured text lists or bullet points

    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
    Negative Logits
    ARY
    0.52
    AR
    0.51
    astre
    0.50
     받았
    0.50
     trasm
    0.48
     활동
    0.48
     위치
    0.48
    ARING
    0.47
    Վ
    0.47
    IOR
    0.47
    POSITIVE LOGITS
    т
    0.44
     livre
    0.43
    тли
    0.43
    ت
    0.42
    mlabeledtr
    0.42
    ли
    0.41
    لت
    0.41
    талия
    0.40
     கிடைக்கும்
    0.40
    ি
    0.40
    Activations Density 0.001%

    No Known Activations