© 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. 22-GEMMASCOPE-RES-131K
    7. 129057
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the literal “>” character (e.g. as used to close HTML tags and in code).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code and version numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ’:
    -0.97
    tamaan
    -0.94
    ₂)
    -0.91
    を
    -0.90
     otros
    -0.89
     ?>>
    -0.88
    "—
    -0.88
    )—
    -0.87
    ↵↵↵
    -0.86
     أهل
    -0.85
    POSITIVE LOGITS
     défauts
    0.97
    えっ
    0.96
    有哪些
    0.95
     parlent
    0.94
    quelles
    0.93
     endast
    0.93
    と書
    0.91
    あー
    0.90
     apapun
    0.90
     に関する
    0.89
    Activations Density 0.067%

    No Known Activations