© 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. 57787
    Prev
    Next
    INDEX
    Explanations

    spiritual and supernatural entities

    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
     مردم
    -0.94
     Tissues
    -0.92
     breeders
    -0.79
     mutagenesis
    -0.79
     REPORTER
    -0.77
     CANDIDATE
    -0.77
    влению
    -0.77
     abusers
    -0.75
    writable
    -0.75
    PORTS
    -0.75
    POSITIVE LOGITS
     beings
    3.03
     entities
    2.41
     entity
    1.93
    entities
    1.84
     creatures
    1.81
     spirits
    1.79
     supernatural
    1.79
    entity
    1.51
     entidades
    1.50
    Entities
    1.48
    Activations Density 0.021%

    No Known Activations