© 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. 45262
    Prev
    Next
    INDEX
    Explanations

    body

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

    The neuron strongly activates on mentions of camera-related terms (e.g. “camera,” “cameras,” “body cameras”), thus detecting references to camera technology.

    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
     stopper
    -0.82
    ombras
    -0.78
    stridium
    -0.73
    bgColor
    -0.73
     bles
    -0.69
    Gut
    -0.67
    iney
    -0.66
    ERTE
    -0.66
     الوطني
    -0.66
    dataType
    -0.66
    POSITIVE LOGITS
     body
    3.16
     Body
    2.55
    body
    2.45
    Body
    2.39
     BODY
    2.16
    BODY
    1.84
     bodys
    1.69
     cuerpo
    1.68
    RequestBody
    1.55
     bodies
    1.53
    Activations Density 0.028%

    No Known Activations