© 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. 63335
    Prev
    Next
    INDEX
    Explanations

    ! and programming constructs

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

    The neuron primarily reacts to standalone exclamation‐mark punctuation tokens (“!”).

    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
     as
    -1.03
     or
    -0.82
     such
    -0.82
     aber
    -0.82
    )
    -0.81
     in
    -0.80
    問題は
    -0.80
    sq
    -0.79
     like
    -0.78
     now
    -0.75
    POSITIVE LOGITS
    FALSE
    0.97
     verdaderos
    0.96
     FALSE
    0.94
    ༣
    0.94
     Gainesville
    0.91
     travailler
    0.91
     dúvida
    0.90
    DOCTYPE
    0.90
     chyb
    0.89
     estándares
    0.88
    Activations Density 0.002%

    No Known Activations