© 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. 10-GEMMASCOPE-RES-131K
    7. 7755
    Prev
    Next
    INDEX
    Explanations

    consciousness, subconsciousness, conscience

    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_10/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
    旆
    -1.96
     mortos
    -1.91
    眥
    -1.87
    recen
    -1.86
    structura
    -1.83
     Their
    -1.73
    tradu
    -1.73
     obligación
    -1.71
    hånd
    -1.70
     necessárias
    -1.70
    POSITIVE LOGITS
     workings
    2.14
     estekak
    1.64
    w
    1.63
    '
    1.55
    l
    1.53
    /
    1.49
    m
    1.48
    各
    1.48
     subconscious
    1.46
     ebb
    1.46
    Activations Density 0.004%

    No Known Activations