© 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. 206025
    Prev
    Next
    INDEX
    Explanations

    you shall go for

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

    list items like "Models:", "Spectrum Comparison", "Reasons:", "rarely life-threatening", "emerging markets", "North, South, East, West", "Plugins like", "Conflict Resolution"

    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
    années
    0.57
    sker
    0.50
    izações
    0.49
    évrier
    0.48
    delim
    0.48
    tails
    0.47
     죄
    0.47
    ingen
    0.47
     透
    0.47
    ssss
    0.46
    POSITIVE LOGITS
     conducir
    0.47
    ETTE
    0.46
     kraju
    0.45
     ampio
    0.45
     shew
    0.45
     plunged
    0.44
    ﺤ
    0.44
     comunque
    0.44
     chairman
    0.43
     নৃ
    0.43
    Activations Density 0.000%

    No Known Activations