© 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. 31014
    Prev
    Next
    INDEX
    Explanations

    Tanner, Tan, Tanwi, Tanya, Tanimoto

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

    The neuron is picking out words containing the character sequence “tan,” e.g. proper names or terms beginning with “Tan.”

    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
     極
    -0.75
     zaś
    -0.73
     =~
    -0.72
     ciclos
    -0.69
    Rene
    -0.69
    buffalo
    -0.69
    Hungary
    -0.68
    uels
    -0.68
     &[
    -0.68
    VOA
    -0.68
    POSITIVE LOGITS
     filament
    0.75
     accuse
    0.74
    äl
    0.74
     VOR
    0.73
     assail
    0.72
     定制
    0.72
    adí
    0.71
    ოლი
    0.71
     coercion
    0.70
    اض
    0.70
    Activations Density 0.024%

    No Known Activations