© 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. 74070
    Prev
    Next
    INDEX
    Explanations

    Yii framework, Blackpool, honeycomb

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

    The neuron fires on uncommon or domain-specific content words—especially proper names (places, organizations) and technical terms.

    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
    ing
    -2.80
    ⎔
    -2.55
     ensure
    -2.52
    齪
    -2.50
    a
    -2.38
    醗
    -2.28
     resistencia
    -2.25
     vast
    -2.23
    Ꮏ
    -2.22
    ↵
    -2.20
    POSITIVE LOGITS
    賔
    2.41
    ра
    2.34
     unſ
    2.34
     GOtt
    2.33
     adhering
    2.31
     Beſ
    2.30
     墊
    2.30
    $,
    2.27
    蹰
    2.27
     Monfieur
    2.23
    Activations Density 0.011%

    No Known Activations