© 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. 104702
    Prev
    Next
    INDEX
    Explanations

    macadamia and make up

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

    The neuron strongly activates on numeric tokens (especially multi‐digit numbers like years or counts).

    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
    !
    -1.08
    ,
    -1.07
    :
    -1.04
    .
    -0.92
     four
    -0.90
     nuevamente
    -0.90
    &
    -0.90
    it
    -0.90
     except
    -0.89
     time
    -0.85
    POSITIVE LOGITS
     ligue
    1.01
     feront
    1.00
     ideen
    0.99
     essentielle
    0.98
     bienfaits
    0.98
     distinguer
    0.97
     comportements
    0.96
     beton
    0.96
     चीज़ों
    0.96
     mädchen
    0.95
    Activations Density 0.067%

    No Known Activations