© 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. 10-GEMMASCOPE-RES-131K
    7. 9923
    Prev
    Next
    INDEX
    Explanations

    test keywords

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

    The neuron flags underscore characters in code identifiers—especially in snake_case function names (e.g. test_*).

    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
     radiador
    -1.62
     głównie
    -1.55
    <bos>
    -1.55
     ligeramente
    -1.54
     rígido
    -1.51
     burbujas
    -1.44
     gefahren
    -1.43
     lámpara
    -1.42
     halbe
    -1.42
     exhibición
    -1.41
    POSITIVE LOGITS
     of
    1.73
     anormal
    1.66
     hommage
    1.51
     this
    1.49
    呖
    1.48
     compren
    1.47
     mereka
    1.42
     serta
    1.41
     extraordin
    1.41
    it
    1.41
    Activations Density 0.004%

    No Known Activations