© 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. 59378
    Prev
    Next
    INDEX
    Explanations

    data concepts

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

    The neuron is specialized in detecting occurrences of the word “data.”

    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
    酲
    -2.00
    𞤢
    -1.78
    ’
    -1.74
    雠
    -1.70
     allemand
    -1.55
     ſta
    -1.49
    髦
    -1.48
     esthétique
    -1.48
    лись
    -1.47
            
    -1.46
    POSITIVE LOGITS
     obti
    1.62
    ى
    1.49
     PUEDE
    1.48
    ⤴
    1.48
     RECOMEND
    1.48
    ffed
    1.48
    遢
    1.45
    
    1.45
     全新
    1.44
     MÁS
    1.42
    Activations Density 0.086%

    No Known Activations