© 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. 22-GEMMASCOPE-RES-131K
    7. 68479
    Prev
    Next
    INDEX
    Explanations

    bigger than

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

    This neuron spots numerical literals (and related numeric comparisons) 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_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
    lamiento
    -0.87
     addition
    -0.85
    +//
    -0.83
     kesadaran
    -0.82
    Schedulers
    -0.81
     Tämä
    -0.81
    losti
    -0.79
    過ごし
    -0.79
    transition
    -0.79
     partage
    -0.78
    POSITIVE LOGITS
     better
    0.98
     بهتر
    0.94
    のほうが
    0.92
     preferable
    0.90
    の方が
    0.90
     Versus
    0.87
     compared
    0.85
    に向
    0.85
     vs
    0.84
    ENDIF
    0.82
    Activations Density 0.005%

    No Known Activations