© 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. 77921
    Prev
    Next
    INDEX
    Explanations

    schematic

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

    This neuron activates on the subword “sche” (i.e. tokens containing the letter sequence “sche”).

    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
     Huntsville
    -0.87
     Simón
    -0.83
     shur
    -0.81
     Huntingdon
    -0.81
     plebe
    -0.81
     adventurers
    -0.79
     Præ
    -0.77
     nro
    -0.76
     calum
    -0.76
     ork
    -0.75
    POSITIVE LOGITS
     Sche
    1.22
    Sche
    0.97
    cay
    0.88
     Arch
    0.83
     Thank
    0.79
     médaille
    0.78
     thank
    0.75
     sche
    0.73
     Sama
    0.72
     quase
    0.72
    Activations Density 0.010%

    No Known Activations