© 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. 57355
    Prev
    Next
    INDEX
    Explanations

    body parts and tissues

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

    descriptions of physical damage or injury to body tissues.

    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
    Legs
    -0.94
     feet
    -0.93
    Feet
    -0.92
    legs
    -0.91
     Legs
    -0.89
     legs
    -0.89
    MouseClicked
    -0.89
     ApiClient
    -0.85
     shoulders
    -0.85
    Foot
    -0.83
    POSITIVE LOGITS
     muscles
    2.66
     bones
    2.52
     muscle
    2.45
     bone
    2.25
    muscle
    2.06
     tendons
    2.03
     skin
    2.02
     nerves
    1.93
     cartilage
    1.86
     flesh
    1.84
    Activations Density 0.098%

    No Known Activations