© 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. 116438
    Prev
    Next
    INDEX
    Explanations

    misbehaving or behaving well

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

    The neuron activates on text describing discipline of children—their mischief, hiding behavior, and the consequences or discussion around disciplining a kid.

    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
     INSPIRE
    -0.89
     persecution
    -0.81
     verlie
    -0.77
     پرورش
    -0.76
     Babies
    -0.73
     Confusion
    -0.72
     VOR
    -0.72
     Pedestrian
    -0.71
    ченным
    -0.70
     herstellen
    -0.70
    POSITIVE LOGITS
     mis
    4.19
    Mis
    2.81
     Mis
    2.64
     behaving
    2.64
    mis
    2.64
     behave
    2.34
     misconduct
    2.30
     behavior
    2.30
     behaved
    2.27
     behaviour
    2.23
    Activations Density 0.050%

    No Known Activations