© 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. 107118
    Prev
    Next
    INDEX
    Explanations

    muscle strength

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

    terms related to physical strength, muscles, and fitness training.

    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
    милия
    -0.84
    Inhalts
    -0.80
    terung
    -0.77
    Ethernet
    -0.75
     congrès
    -0.74
    ticamente
    -0.73
    StandardCharsets
    -0.72
     молит
    -0.71
     бес
    -0.71
    TiO
    -0.71
    POSITIVE LOGITS
     strength
    3.66
     Strength
    2.89
    strength
    2.77
    Strength
    2.77
     strengthening
    2.53
     STRENGTH
    2.45
     strengthen
    2.31
    STRENGTH
    2.30
     streng
    1.98
     muscle
    1.94
    Activations Density 0.041%

    No Known Activations