© 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. 118412
    Prev
    Next
    INDEX
    Explanations

    titles of books and names

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

    This neuron fires on prominent title or heading words (i.e. section‐header tokens).

    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
     BLOG
    -0.81
    Due
    -0.78
     للس
    -0.76
    わない
    -0.74
     Recycled
    -0.73
     clouds
    -0.73
     Huffington
    -0.73
    vén
    -0.73
    guer
    -0.72
     erfordert
    -0.72
    POSITIVE LOGITS
     queer
    0.96
    dotenv
    0.83
    CUIT
    0.82
    Congratulations
    0.81
    mmons
    0.81
    果汁
    0.80
     internet
    0.80
    柑
    0.80
     Hanya
    0.79
     MFA
    0.79
    Activations Density 0.030%

    No Known Activations