© 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. 108739
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    The neuron fires most strongly on past‐tense “-ed” verb forms (e.g. “dotted,” “crossed”).

    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
    Portland
    -0.73
    rike
    -0.67
    ătoare
    -0.65
     immunization
    -0.65
    itology
    -0.65
     sounding
    -0.64
     порядок
    -0.63
     Warbler
    -0.63
    arum
    -0.63
    вар
    -0.62
    POSITIVE LOGITS
     vải
    0.68
     concepción
    0.68
     forfeit
    0.67
    scarlet
    0.66
     digne
    0.65
    realloc
    0.65
     classé
    0.64
     nhằm
    0.64
    wendungs
    0.63
    ราช
    0.63
    Activations Density 0.044%

    No Known Activations