© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11941
    Prev
    Next
    INDEX
    Explanations

    exit status codes

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

    The neuron fires on numeric tokens (sequences of digits).

    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
    都要
    -0.80
    وی
    -0.78
    ایی
    -0.76
     Gilmore
    -0.75
    ˝
    -0.74
    +#+
    -0.74
    ävät
    -0.73
    TCHAR
    -0.73
    OLED
    -0.72
    towym
    -0.72
    POSITIVE LOGITS
     exit
    2.39
     Exit
    2.08
    Exit
    1.80
    exit
    1.80
     EXIT
    1.76
     exits
    1.48
    退出
    1.43
    EXIT
    1.42
     exited
    1.41
     $?
    1.18
    Activations Density 0.032%

    No Known Activations