© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103737
    Prev
    Next
    INDEX
    Explanations

    the scene of an event

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

    This neuron detects references to an incident location (e.g. “scene,” “site,” “spot”) and related actions of people arriving at or responding to that place.

    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
     pregi
    -0.76
    床上
    -0.71
    Highlight
    -0.70
     sentado
    -0.70
    erah
    -0.68
     Dingen
    -0.68
     amoureux
    -0.68
     Dinge
    -0.67
     Developed
    -0.67
    よ
    -0.66
    POSITIVE LOGITS
     scene
    5.22
    scene
    3.63
     scenes
    3.53
     Scene
    3.31
    Scene
    3.27
    SCENE
    2.89
     SCENE
    2.86
     escena
    2.75
     scène
    2.67
    現場
    2.63
    Activations Density 0.044%

    No Known Activations