© 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. 99076
    Prev
    Next
    INDEX
    Explanations

    respond to

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

    The neuron detects occurrences of “respond” (and its morphological variants like responded or responsiveness).

    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
     einigen
    -2.77
    
    -2.66
    たちの
    -2.66
    外的
    -2.64
    dientemente
    -2.63
    r
    -2.58
     keinem
    -2.56
     langen
    -2.56
     jenem
    -2.56
     neuen
    -2.52
    POSITIVE LOGITS
    “
    2.89
     ferrovia
    2.52
    柃
    2.48
    
    2.47
    綃
    2.44
    ࣭
    2.44
    佧
    2.42
     promessa
    2.42
    罢了
    2.39
    桫
    2.38
    Activations Density 0.009%

    No Known Activations