© 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. 22-GEMMASCOPE-RES-131K
    4. 467
    Prev
    Next
    INDEX
    Explanations

    function definitions or includes

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

    The neuron fires strongly on tokens that are C/C++ (and related) file-extension or module-import names ending in “.pp” or “.hpp.”

    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
     only
    -1.40
     then
    -1.36
     at
    -1.35
     this
    -1.21
     their
    -1.20
     those
    -1.18
     even
    -1.14
     from
    -1.12
     an
    -1.12
     before
    -1.07
    POSITIVE LOGITS
    donc
    1.44
    création
    1.30
    wasn
    1.30
    がとても
    1.28
     maintenant
    1.23
    кзак
    1.21
    vidéo
    1.21
    がたくさん
    1.20
    ţele
    1.19
    weren
    1.19
    Activations Density 0.000%

    No Known Activations