© 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. 56797
    Prev
    Next
    INDEX
    Explanations

    guest speakers and professionals

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

    The neuron detects sentence-ending punctuation (full stops).

    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
    breviations
    -1.09
    ceptable
    -0.95
    zzzz
    -0.90
    *&
    -0.89
     "];
    -0.88
    titch
    -0.86
    dateien
    -0.84
    遗传
    -0.84
    tyimages
    -0.83
    GetBytes
    -0.83
    POSITIVE LOGITS
     guest
    3.59
    guest
    2.56
     visiting
    2.45
     Guest
    2.38
    Guest
    2.34
     speakers
    1.99
     guests
    1.97
     industry
    1.97
     visits
    1.95
    GUEST
    1.88
    Activations Density 0.030%

    No Known Activations