© 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. 100121
    Prev
    Next
    INDEX
    Explanations

    forearm contexts

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

    The neuron strongly activates on occurrences of the anatomical term “forearm.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    </b>
    -3.09
    靫
    -2.75
     regal
    -2.63
    section
    -2.58
    
    -2.39
     fruto
    -2.33
    皤
    -2.30
    甞
    -2.27
    灃
    -2.27
    跟随
    -2.25
    POSITIVE LOGITS
    The
    3.33
    媖
    3.08
    '
    2.92
    </h3>
    2.81
    It
    2.73
    媄
    2.67
    r
    2.64
     of
    2.64
    l
    2.55
    傒
    2.48
    Activations Density 0.015%

    No Known Activations