© 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. 98747
    Prev
    Next
    INDEX
    Explanations

    interior nose

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

    numerical measurements or statistics related to physical attributes (like height, weight, dimensions).

    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_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
     Corners
    -0.79
    reich
    -0.77
     Cib
    -0.75
     dermatitis
    -0.73
    lector
    -0.70
     milk
    -0.69
    PV
    -0.69
     ethers
    -0.68
     Laredo
    -0.68
    角
    -0.67
    POSITIVE LOGITS
     interior
    1.63
     nose
    1.45
    interior
    1.43
    Nose
    1.39
     Nose
    1.27
    nose
    1.16
     Interior
    1.11
     DT
    1.11
     INTERIOR
    1.09
    INTERIOR
    1.09
    Activations Density 0.013%

    No Known Activations