© 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. 22-GEMMASCOPE-RES-131K
    7. 66060
    Prev
    Next
    INDEX
    Explanations

    code delimiters and separators

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

    The neuron is highly active on very short, non‐dictionary tokens in code or markup—i.e. single characters or short strings of digits, punctuation, or hex‐style symbols.

    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
     varias
    -1.23
     while
    -1.19
     where
    -1.17
     relatively
    -1.16
     intricate
    -1.10
     more
    -1.09
    二日
    -1.09
     most
    -1.05
     numerous
    -1.05
     several
    -1.02
    POSITIVE LOGITS
     '-';
    1.18
     DialogInterface
    1.16
     '-
    1.16
     yz
    1.16
    mrow
    1.13
     $*
    1.12
     plut
    1.10
     البرنامج
    1.09
     koi
    1.09
    TUAL
    1.09
    Activations Density 0.007%

    No Known Activations