© 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. 129735
    Prev
    Next
    INDEX
    Explanations

    Athena, pneumococcal, Thai script, Rust attributes, code comments

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

    The neuron fires most strongly on standalone proper names (especially project or code‐component names) often found in comments.

    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
     multitude
    -2.88
    pecabe
    -2.52
     horrific
    -2.47
    e
    -2.41
     nascent
    -2.41
    kého
    -2.38
    سجيل
    -2.36
     appalling
    -2.36
     intoxicating
    -2.31
     enlightening
    -2.30
    POSITIVE LOGITS
    鵙
    2.48
     和
    2.28
    姌
    2.23
     strane
    2.20
    .
    2.16
    臏
    2.08
     dispar
    2.02
     furg
    2.02
     และ
    1.99
     supp
    1.98
    Activations Density 0.004%

    No Known Activations