© 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. 58845
    Prev
    Next
    INDEX
    Explanations

    physical characteristics and health

    np_acts-logits-general · gemini-2.5-flash-lite

    physical attributes or characteristics related to health, body, or objects.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
                    
    -1.94
    I
    -1.74
    );
    -1.74
     Now
    -1.61
    i
    -1.57
    By
    -1.54
    ("
    -1.53
          
    -1.52
       
    -1.50
     B
    -1.48
    POSITIVE LOGITS
     physical
    2.06
    продам
    1.91
     fysis
    1.90
    physical
    1.84
    ズニー
    1.81
     körper
    1.76
    <bos>
    1.75
    ſu
    1.75
    ⌵
    1.72
    Physical
    1.71
    Activations Density 0.045%

    No Known Activations