© 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. 10-GEMMASCOPE-RES-131K
    7. 8653
    Prev
    Next
    INDEX
    Explanations

    word beginnings followed by continuations

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

    The neuron responds strongly to capitalized name or title fragments (i.e. tokens that begin with an uppercase letter and form part of a proper noun).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     promove
    -1.88
    蕺
    -1.80
     lamenta
    -1.74
     ofere
    -1.73
     podrá
    -1.72
     motorista
    -1.72
    
    -1.72
     arrend
    -1.71
    mavi
    -1.71
    льная
    -1.70
    POSITIVE LOGITS
    _
    2.81
     these
    2.16
     from
    1.95
    From
    1.91
    on
    1.91
     all
    1.88
    //
    1.84
    all
    1.80
    ’,
    1.80
    for
    1.79
    Activations Density 0.161%

    No Known Activations