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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117669
    Prev
    Next
    INDEX
    Explanations

    supernatural beings and spirits

    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
    甥
    -0.79
    destru
    -0.75
    Quest
    -0.71
     गो
    -0.71
     タワー
    -0.70
    ֶּ
    -0.69
     douceur
    -0.69
    诠
    -0.68
    стойчи
    -0.68
    Nova
    -0.67
    POSITIVE LOGITS
     spirits
    1.36
     incub
    1.34
     bans
    1.29
     sprites
    1.23
     Bans
    1.23
     succ
    1.16
     demons
    1.11
     Incub
    1.08
     demon
    1.08
     Centa
    1.05
    Activations Density 0.034%

    No Known Activations