© 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. 59233
    Prev
    Next
    INDEX
    Explanations

    pin connections and quantities

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

    The neuron activates on numeric specification tokens, especially measurement values and pin numbers.

    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
    でしたが
    -1.52
     eşofman
    -1.51
     profils
    -1.49
     scris
    -1.48
     castel
    -1.45
     bords
    -1.44
     Matrices
    -1.43
    Literatuur
    -1.43
     autorisation
    -1.43
     pommes
    -1.43
    POSITIVE LOGITS
    on
    1.91
     to
    1.81
    ৢ
    1.69
    '
    1.66
    呵呵
    1.66
    有不少
    1.57
     austere
    1.55
    xvi
    1.55
     indelible
    1.46
    xvii
    1.45
    Activations Density 0.026%

    No Known Activations