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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77510
    Prev
    Next
    INDEX
    Explanations

    Immortalization, Qin Kanying, Widener, trials, Comparison, Specific IgE

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

    The neuron fires on tokens that begin with an uppercase letter—e.g. proper names, capitalized terms, or 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
    Fakta
    -0.80
    Pengertian
    -0.80
    pří
    -0.77
     Дж
    -0.72
    ülés
    -0.71
     riktigt
    -0.71
    ässig
    -0.70
     Köln
    -0.69
     tiens
    -0.69
     Deutsche
    -0.69
    POSITIVE LOGITS
    tranno
    0.86
    urias
    0.84
    kko
    0.83
    <h6>
    0.81
    setzen
    0.79
     targeting
    0.79
     identif
    0.79
    čně
    0.77
    WRP
    0.77
     dị
    0.76
    Activations Density 0.000%

    No Known Activations