© 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. 13562
    Prev
    Next
    INDEX
    Explanations

    maximum, less, city, signed, none

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

    The neuron primarily fires on numeric tokens (i.e. any standalone numbers).

    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
    [];
    -1.01
    чните
    -0.93
    Markers
    -0.89
    蹂
    -0.87
    עות
    -0.85
    Others
    -0.85
    Válasz
    -0.85
     queste
    -0.85
    鸠
    -0.84
    ahora
    -0.84
    POSITIVE LOGITS
     not
    1.57
     no
    1.49
     only
    1.31
     less
    1.03
     both
    1.02
     none
    0.98
     mainly
    0.96
    岁
    0.93
     after
    0.90
     still
    0.90
    Activations Density 0.008%

    No Known Activations