© 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. 10-GEMMASCOPE-RES-131K
    7. 105664
    Prev
    Next
    INDEX
    Explanations

    code, formal names, mathematics

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

    opening parentheses in function declarations and calls in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron strongly responds to open-parenthesis tokens, especially those marking function calls or definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     preocupado
    -1.63
    }
    -1.60
     desbloquear
    -1.59
     concentrado
    -1.59
    mika
    -1.59
     étan
    -1.55
     podremos
    -1.55
     tocado
    -1.52
     instrumentos
    -1.52
     inoxidable
    -1.47
    POSITIVE LOGITS
     with
    1.98
     from
    1.88
     all
    1.87
     in
    1.70
     of
    1.68
     who
    1.64
     for
    1.63
     like
    1.52
     those
    1.51
     at
    1.44
    Activations Density 0.002%

    No Known Activations