© 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. 92973
    Prev
    Next
    INDEX
    Explanations

    physical versus non-physical concepts

    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
     ian
    -0.85
    ⸱
    -0.83
    umbus
    -0.80
     rodriguez
    -0.79
    blat
    -0.77
     pite
    -0.77
    RENDER
    -0.76
    balancing
    -0.76
    zzz
    -0.76
    don
    -0.75
    POSITIVE LOGITS
     mental
    2.56
     spiritual
    2.38
     psychological
    2.33
     intangible
    2.23
    精神
    1.93
     invisible
    1.91
     духов
    1.82
    spiritual
    1.80
     metaphorical
    1.77
     intellectual
    1.77
    Activations Density 0.096%

    No Known Activations