© 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. 34-GEMMASCOPE-RES-131K
    7. 2970
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by code elements

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

    The neuron fires on tokens that consist of numeric literals (i.e. digits or numbers) in code or configuration.

    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
     căr
    -0.81
     mauri
    -0.80
    デフォ
    -0.79
    PRF
    -0.78
     Graduates
    -0.78
     pelatih
    -0.77
     equidist
    -0.77
    崴
    -0.75
    tvar
    -0.75
     kabát
    -0.75
    POSITIVE LOGITS
     source
    0.93
    ActionPerformed
    0.92
     computer
    0.91
     Computer
    0.90
     occurred
    0.88
     outcome
    0.86
     affected
    0.85
     distinción
    0.85
     involved
    0.84
     actionPerformed
    0.84
    Activations Density 0.041%

    No Known Activations