© 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. 84076
    Prev
    Next
    INDEX
    Explanations

    statistical significance

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

    The neuron responds to standalone numerical tokens (digits and 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
     pantal
    -1.57
     tempel
    -1.55
     berge
    -1.49
     tille
    -1.48
     magasiner
    -1.48
     velours
    -1.47
     guir
    -1.47
     siff
    -1.46
     beina
    -1.45
     bronz
    -1.45
    POSITIVE LOGITS
    4
    1.19
    0
    1.16
    3
    1.15
    *
    1.13
     not
    1.13
     three
    1.13
    8
    1.12
      
    1.09
     T
    1.08
    7
    1.08
    Activations Density 0.002%

    No Known Activations