© 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. 34-GEMMASCOPE-RES-131K
    7. 108732
    Prev
    Next
    INDEX
    Explanations

    class declarations

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

    The neuron strongly activates on occurrences of the keyword “class” in code (i.e. references to Java class definitions or uses).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     of
    -1.80
    作って
    -1.13
    :
    -1.13
    一旁的
    -1.11
    使って
    -1.07
     by
    -1.02
     only
    -0.97
     Beispiele
    -0.97
    眼前的
    -0.97
     francês
    -0.96
    POSITIVE LOGITS
     traditionnels
    1.19
     permisos
    1.15
    ėj
    1.09
     gjort
    1.09
     religiosos
    1.09
    kuchen
    1.07
    سین
    1.06
     لكل
    1.05
    rocław
    1.05
     específicos
    1.05
    Activations Density 0.006%

    No Known Activations