© 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. 22-GEMMASCOPE-RES-131K
    7. 34395
    Prev
    Next
    INDEX
    Explanations

    physical and psychological

    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_22/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
     backstory
    -1.03
    onite
    -0.93
    ३
    -0.91
     bekämp
    -0.88
    ześnie
    -0.87
    MessageTagHelper
    -0.85
     stehenden
    -0.84
     OGSÅ
    -0.83
    velu
    -0.83
     самостоятельно
    -0.82
    POSITIVE LOGITS
     physical
    1.89
     bodily
    1.39
    physical
    1.31
    PHYSICAL
    1.30
     Physical
    1.24
     physically
    1.23
    Physical
    1.19
     equipment
    1.16
     fysis
    1.14
     hardware
    1.06
    Activations Density 0.085%

    No Known Activations