© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8012
    Prev
    Next
    INDEX
    Explanations

    findAll function calls, Rog, Ottawa, Peterson

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

    The neuron activates on tokens containing uppercase letters—e.g. proper names or capitalized identifiers.

    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
    ’
    -6.16
    "
    -3.50
    ,.
    -3.42
    ,,
    -3.16
    ]
    -3.14
    并没有
    -2.80
     ‚
    -2.78
    1
    -2.75
    /
    -2.67
     ´
    -2.55
    POSITIVE LOGITS
    猡
    2.81
    骓
    2.78
    𓋼
    2.73
    ⦊
    2.53
    celotti
    2.52
    èvent
    2.45
    驟
    2.38
    ｨ
    2.36
     powierzch
    2.34
    
    2.34
    Activations Density 0.009%

    No Known Activations