© 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. 20043
    Prev
    Next
    INDEX
    Explanations

    Eileen, punctuation, append

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

    The neuron strongly activates on tokens that begin with a capital letter (proper nouns or other uppercase words).

    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
    谁能
    -2.61
     partake
    -2.39
    琤
    -2.38
    卨
    -2.38
    butuhkan
    -2.36
    讴
    -2.36
    ادية
    -2.31
    瓩
    -2.28
    箝
    -2.27
     alterar
    -2.23
    POSITIVE LOGITS
    a
    2.66
    <em>
    2.64
    ↵
    2.53
    很是
    2.52
    或者是
    2.42
    ”
    2.27
     -
    2.25
    ”-
    2.23
    or
    2.20
    0
    2.20
    Activations Density 0.001%

    No Known Activations