© 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. 15567
    Prev
    Next
    INDEX
    Explanations

    by and of

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

    The neuron responds to numeric expressions (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
     is
    -1.27
     where
    -1.26
     instead
    -1.16
     bekom
    -1.13
     something
    -1.13
    améli
    -1.13
    licants
    -1.13
    stacles
    -1.13
     PLWABN
    -1.09
    salms
    -1.07
    POSITIVE LOGITS
    middels
    1.49
     people
    1.44
    俱乐
    1.25
     héro
    1.21
     män
    1.21
     kompres
    1.20
     Brésil
    1.18
     [{
    1.18
     forfatter
    1.17
    腭
    1.16
    Activations Density 0.084%

    No Known Activations