© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84928
    Prev
    Next
    INDEX
    Explanations

    generate with income

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

    This neuron selectively fires on tokens that begin with a capital letter—e.g. title‐style words and code identifiers.

    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
     Kendall
    -0.69
     Milch
    -0.69
     希
    -0.66
     Dev
    -0.64
     estrella
    -0.64
     Fran
    -0.63
     Georges
    -0.63
    亮相
    -0.63
     Drew
    -0.62
    sentinel
    -0.62
    POSITIVE LOGITS
    ecta
    0.93
    attack
    0.82
     lojas
    0.81
     Inhibitors
    0.77
    ksjoner
    0.77
    xbb
    0.75
    Giant
    0.75
    帜
    0.75
    Formazione
    0.74
     géant
    0.74
    Activations Density 0.004%

    No Known Activations