© 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. 63246
    Prev
    Next
    INDEX
    Explanations

    structural support, legal proceedings

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

    The neuron chiefly detects occurrences of the word “scaffold” or its variant “scaffolding.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    hmac
    -0.80
    yo
    -0.77
    sso
    -0.73
     GPIO
    -0.72
    toi
    -0.70
     Zeiten
    -0.67
     imple
    -0.67
    카
    -0.66
     Reserved
    -0.66
     Had
    -0.66
    POSITIVE LOGITS
    bonjour
    0.75
    来得
    0.75
    精确
    0.73
    Mejor
    0.71
    antigua
    0.71
    罗斯
    0.69
    Permit
    0.68
    ᠰ
    0.68
    Kou
    0.68
    ίου
    0.67
    Activations Density 0.062%

    No Known Activations