© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38750
    Prev
    Next
    INDEX
    Explanations

    numbers following "www"

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

    This neuron responds to multi‐digit numeric tokens, i.e. large numbers 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
     by
    -1.36
     one
    -1.31
     or
    -1.26
     so
    -1.14
     that
    -1.14
     as
    -1.13
     after
    -1.11
     within
    -1.11
     with
    -1.05
     at
    -1.04
    POSITIVE LOGITS
     скриншот
    1.04
    urii
    1.02
    őség
    1.00
    MfG
    0.97
    thumbsup
    0.97
     grumpy
    0.97
    Wellness
    0.95
     supérieurs
    0.95
     ſtate
    0.95
     decimals
    0.94
    Activations Density 0.056%

    No Known Activations