© 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. 30411
    Prev
    Next
    INDEX
    Explanations

    whereabouts of missing people

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

    The neuron fires on interrogative elements—question words (e.g. “where,” “what,” “did”) and question-mark punctuation—highlighting the presence of a question.

    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
     betrachten
    -0.93
     hjäl
    -0.85
    
    -0.82
    ieť
    -0.81
     atriz
    -0.79
     olhando
    -0.79
    ства
    -0.79
     gostaria
    -0.78
    来た
    -0.78
    xhr
    -0.77
    POSITIVE LOGITS
     whereabouts
    3.42
     disappeared
    2.14
     disappearance
    2.11
     missing
    1.74
    Where
    1.70
     disappear
    1.67
     wherea
    1.67
    WHERE
    1.66
     location
    1.59
     vanished
    1.55
    Activations Density 0.031%

    No Known Activations