© 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. 10-GEMMASCOPE-RES-131K
    7. 45572
    Prev
    Next
    INDEX
    Explanations

    Taylor Swift, court, open beta

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

    This neuron fires on tokens that begin new lines or indented segments (i.e. tokens appearing immediately after line breaks and whitespace).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    iteten
    -1.58
    //{
    -1.52
     Following
    -1.50
    </h4>
    -1.49
     sogar
    -1.48
    );
    -1.48
     varför
    -1.47
     In
    -1.38
     simplemente
    -1.38
    𝟮
    -1.38
    POSITIVE LOGITS
    OUTUBE
    1.60
     další
    1.48
     mauva
    1.45
     jezt
    1.45
     another
    1.38
     ガード
    1.35
     farmaco
    1.33
     arrivent
    1.32
     funcionam
    1.31
     today
    1.30
    Activations Density 0.068%

    No Known Activations