© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26713
    Prev
    Next
    INDEX
    Explanations

    approximate numerical values

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

    The neuron activates on numeric values (including decimals) representing measurements or quantities.

    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
     pimenta
    -0.93
     более
    -0.91
     more
    -0.89
     embaj
    -0.87
     Aspekte
    -0.85
     сможет
    -0.84
     such
    -0.84
    zeń
    -0.82
    úmeros
    -0.81
    惊喜
    -0.80
    POSITIVE LOGITS
     вслед
    1.00
    Certain
    0.96
    OOTDTY
    0.94
     Wartawan
    0.94
     Danach
    0.90
     sagt
    0.88
     Certain
    0.87
     käyt
    0.85
     helft
    0.84
    Agreed
    0.84
    Activations Density 0.047%

    No Known Activations