© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86966
    Prev
    Next
    INDEX
    Explanations

    code log statements

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

    The neuron activates on logging or debug-print calls (e.g. “Log.*” or “log.Printf”).

    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
     esteemed
    -1.84
    ༛
    -1.80
     producen
    -1.70
    胫
    -1.66
    obrázek
    -1.66
    alain
    -1.65
     ancha
    -1.64
    Chúng
    -1.63
     producent
    -1.62
     doba
    -1.62
    POSITIVE LOGITS
    8
    2.39
    6
    2.19
    2
    2.16
    3
    2.09
    5
    2.06
    4
    2.05
    1
    1.88
    7
    1.84
    .
    1.80
    9
    1.70
    Activations Density 0.001%

    No Known Activations