© 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. 67743
    Prev
    Next
    INDEX
    Explanations

    joint flexion and extension

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

    The neuron strongly activates on anatomical terms for tendons and related joint‐movement words (e.g. extensor, flexor, flexion).

    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
    躥
    -2.02
    頽
    -1.79
    闪烁
    -1.55
     these
    -1.47
    prom
    -1.44
    结局
    -1.43
     barnet
    -1.43
    最后由
    -1.41
     Estos
    -1.38
    作战
    -1.38
    POSITIVE LOGITS
    colección
    1.63
    1
    1.59
    嫫
    1.58
    6
    1.54
     motocicletas
    1.52
     realizada
    1.47
     and
    1.45
    非常
    1.45
     \&
    1.43
    超過
    1.40
    Activations Density 0.052%

    No Known Activations