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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50220
    Prev
    Next
    INDEX
    Explanations

    social functioning and adaptation

    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
     Physically
    -0.84
     premed
    -0.80
    ラック
    -0.79
     colectiva
    -0.78
    ƭ
    -0.76
     meditations
    -0.76
    螂
    -0.75
     空間
    -0.74
     pratiquer
    -0.73
    PHYSICS
    -0.73
    POSITIVE LOGITS
     adjustment
    2.06
     functioning
    1.91
     Adjustment
    1.88
     adaptive
    1.73
    adjustment
    1.68
     adaptation
    1.64
    Adjustment
    1.60
    adaptive
    1.52
     adjustments
    1.51
    functioning
    1.46
    Activations Density 0.108%

    No Known Activations