© 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. 72821
    Prev
    Next
    INDEX
    Explanations

    saliva

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

    numbers in news articles and journalistic writing.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects numeric expressions (numbers, years, quantities) in the text.

    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
     to
    -1.27
     from
    -1.22
     neop
    -1.13
     most
    -1.05
     at
    -1.02
     on
    -0.99
     necessary
    -0.96
     deliciosa
    -0.96
     quite
    -0.96
     what
    -0.94
    POSITIVE LOGITS
     móds
    1.09
     aqueles
    1.09
     çantası
    1.08
     THOSE
    1.05
    READ
    1.04
     prévoit
    1.03
     nationales
    1.02
    readdir
    1.00
     heilige
    1.00
     Systeme
    1.00
    Activations Density 0.009%

    No Known Activations