© 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. 99882
    Prev
    Next
    INDEX
    Explanations

    additional information or quotes

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

    The neuron strongly responds to standalone punctuation tokens—especially sentence‐ending periods, smart apostrophes/quotes, and dashes—marking sentence boundaries or stylistic separators.

    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
     but
    -2.23
     it
    -1.74
    humidité
    -1.38
     BUT
    -1.34
    but
    -1.29
     there
    -1.24
     двох
    -1.21
     verschill
    -1.20
    But
    -1.19
     But
    -1.16
    POSITIVE LOGITS
     “
    1.54
     additional
    1.51
     Additionally
    1.36
     according
    1.33
    此次
    1.29
     said
    1.23
     "
    1.21
     additionally
    1.18
     added
    1.15
    Additional
    1.15
    Activations Density 0.053%

    No Known Activations