© 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. 3580
    Prev
    Next
    INDEX
    Explanations

    Read More

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

    The neuron activates on interface metadata elements showing reading‐count or “more” links—i.e. tokens like “Read <number>” and “More <number>.”

    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
     voetballer
    -0.81
     стакан
    -0.81
     इस
    -0.77
    Enviado
    -0.75
     IndexError
    -0.73
    насти
    -0.71
     this
    -0.71
     kinds
    -0.71
     Ausblick
    -0.71
    家族
    -0.70
    POSITIVE LOGITS
     wikipagina
    0.83
    ="&#
    0.81
     入っ
    0.80
    ☆☆☆☆☆
    0.78
    ürtel
    0.78
     Simón
    0.76
     ПОД
    0.75
    zeko
    0.75
    HERE
    0.75
    ण्ड
    0.75
    Activations Density 0.002%

    No Known Activations