© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92243
    Prev
    Next
    INDEX
    Explanations

    May I / This invention / People Water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plantillas
    -0.73
    enin
    -0.71
     automat
    -0.71
    kologie
    -0.70
    IBase
    -0.69
     Ligue
    -0.69
    FileInfo
    -0.68
    Chiara
    -0.68
    itake
    -0.66
     gobern
    -0.65
    POSITIVE LOGITS
     FAL
    0.76
     Veh
    0.74
     Consolidated
    0.74
     Sand
    0.71
     inflex
    0.69
    ॉग
    0.69
     sandbox
    0.69
    miya
    0.69
    IPA
    0.68
     Clic
    0.68
    Activations Density 0.069%

    No Known Activations