© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32741
    Prev
    Next
    INDEX
    Explanations

    making cuts and modifications

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

    The neuron is detecting the second‐person question/request framing—words like “you,” “any,” “to,” “do,” and “?” that occur in how-to or advice-seeking queries.

    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
    čené
    -0.88
     chimiques
    -0.83
    ENCER
    -0.83
     trocken
    -0.77
    CONTEXT
    -0.77
    EOL
    -0.77
    comic
    -0.76
    ルトン
    -0.76
    蔽
    -0.75
    alım
    -0.75
    POSITIVE LOGITS
     cut
    2.06
     drill
    1.82
     drilling
    1.80
     modification
    1.75
    cut
    1.66
     cutting
    1.61
     modifications
    1.57
     drilled
    1.57
    Drill
    1.51
     Drill
    1.50
    Activations Density 0.024%

    No Known Activations