© 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. 34-GEMMASCOPE-RES-131K
    7. 99262
    Prev
    Next
    INDEX
    Explanations

    OBS streaming and capture

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

    The neuron is activated by numeric tokens—i.e. any numbers, dates, version numbers, or other digit strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ופת
    -0.73
    ȵ
    -0.69
    捜査
    -0.69
     trastornos
    -0.68
     poliéster
    -0.68
     Provinz
    -0.68
    hotos
    -0.68
     spraying
    -0.67
    érial
    -0.67
    IMDB
    -0.67
    POSITIVE LOGITS
     OBS
    1.50
    OBS
    1.32
    配信
    1.22
     配信
    1.05
    Capture
    1.05
     capture
    1.03
    obs
    1.02
     Stream
    0.95
     Capture
    0.95
     Twitch
    0.94
    Activations Density 0.012%

    No Known Activations