© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29909
    Prev
    Next
    INDEX
    Explanations

    asking for the best way

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

    The neuron is basically a number detector—it fires strongly on tokens made up of multi‐digit numerals.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    hausen
    -0.82
    ichè
    -0.79
    ект
    -0.77
    不相
    -0.75
     temáticas
    -0.75
     สำ
    -0.74
    entuh
    -0.73
    owskiego
    -0.73
     жы
    -0.73
    ADOW
    -0.73
    POSITIVE LOGITS
     efficient
    2.28
     easiest
    2.20
     quickest
    2.09
     effective
    2.02
     simplest
    1.92
     easy
    1.88
     easier
    1.80
     sure
    1.75
    efficient
    1.63
    effective
    1.59
    Activations Density 0.186%

    No Known Activations