© 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. 22-GEMMASCOPE-RES-131K
    7. 25005
    Prev
    Next
    INDEX
    Explanations

    current or previous states

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

    This neuron activates on common English function words (e.g. articles, pronouns, and prepositions).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     högre
    -1.01
     pomiędzy
    -0.98
    起来的
    -0.97
    tasche
    -0.96
    Fitment
    -0.96
    了不少
    -0.96
     مانند
    -0.95
     لان
    -0.95
     tampoco
    -0.94
    –
    -0.94
    POSITIVE LOGITS
     currently
    3.45
     existing
    3.23
     current
    3.19
     previous
    3.02
     already
    2.98
     previously
    2.72
    currently
    2.31
    Currently
    2.30
     presently
    2.27
    เดิม
    2.05
    Activations Density 0.142%

    No Known Activations