© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40043
    Prev
    Next
    INDEX
    Explanations

    special characters and code delimiters

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

    The neuron responds to long runs of the same token (e.g. “CCCC…”, “;;;;…”, “AAAAAAAA…”), i.e. sequences of repeated single characters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     and
    -3.03
     our
    -2.33
     this
    -2.13
     at
    -2.08
     an
    -2.03
     with
    -2.02
     शुर
    -1.94
     new
    -1.93
     as
    -1.90
     on
    -1.87
    POSITIVE LOGITS
    </i>
    2.44
    to
    2.23
    —“
    2.03
    ?”
    2.00
    ”-
    1.98
     diriger
    1.89
    as
    1.88
     ";
    1.87
    </h3>
    1.85
    al
    1.84
    Activations Density 0.020%

    No Known Activations