© 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. 3861
    Prev
    Next
    INDEX
    Explanations

    variable definition and assignment

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

    The neuron detects numeric literal tokens (integer or floating‐point constants) in code.

    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
     miniaturka
    -1.48
     поддержка
    -1.45
    respectively
    -1.45
     komplet
    -1.43
    翃
    -1.42
     ejercicios
    -1.42
    neither
    -1.41
    跸
    -1.41
    usually
    -1.40
     ekip
    -1.40
    POSITIVE LOGITS
     one
    2.31
     with
    2.30
     after
    1.99
     first
    1.70
     from
    1.69
     began
    1.53
     like
    1.52
     because
    1.51
    After
    1.49
    One
    1.47
    Activations Density 0.019%

    No Known Activations