© 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. 99332
    Prev
    Next
    INDEX
    Explanations

    abrasive material

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

    The neuron detects technical terms related to abrasive materials and sanding devices.

    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
     mechanical
    -0.77
    matsu
    -0.76
    Pla
    -0.76
     Est
    -0.73
    Cos
    -0.71
    maschinen
    -0.71
     Mechanical
    -0.71
     Esk
    -0.71
    omie
    -0.70
     Pla
    -0.70
    POSITIVE LOGITS
     weld
    0.94
     welds
    0.93
     welded
    0.84
     aggressiveness
    0.80
     bacio
    0.77
    ベート
    0.76
     Ravenna
    0.75
     vacanza
    0.74
     Aggression
    0.74
    糶
    0.72
    Activations Density 0.008%

    No Known Activations