© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66138
    Prev
    Next
    INDEX
    Explanations

    ! important

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

    The neuron responds to exclamation marks (sequences of “!”), marking emphatic punctuation.

    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
    !
    -1.86
    !!
    -1.21
    !\
    -1.14
    !
    
    -1.08
    !$
    -1.07
    !<
    -1.03
    ested
    -0.98
    !")
    
    -0.95
    !</
    -0.94
     リボン
    -0.93
    POSITIVE LOGITS
    ....
    1.11
    These
    0.98
    当代
    0.95
    .....
    0.95
    Also
    0.93
    Encyklopedia
    0.91
    ’,
    0.91
    @#
    0.89
    Donc
    0.88
    ciutto
    0.88
    Activations Density 0.023%

    No Known Activations