© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103479
    Prev
    Next
    INDEX
    Explanations

    variable declarations

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

    the word "String" as a data type declaration in programming code.

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

    The neuron strongly activates on programming‐language type identifiers (e.g. “String”, “int”, “u8”, “Type”).

    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
     muerta
    -1.66
     sentada
    -1.56
    ทั้ง
    -1.42
     pesada
    -1.38
     cortada
    -1.34
    owohl
    -1.34
     pintada
    -1.28
    ATUM
    -1.28
     favorita
    -1.27
    Sortie
    -1.27
    POSITIVE LOGITS
                
    1.51
     is
    1.50
     żeby
    1.49
     "
    1.40
    in
    1.40
                 
    1.39
     Priester
    1.32
    1.30
     шести
    1.29
    }}},
    1.28
    Activations Density 0.006%

    No Known Activations