© 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. 72119
    Prev
    Next
    INDEX
    Explanations

    code or markup delimiters

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

    The neuron detects standalone numeric tokens (sequences of digits).

    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
     hés
    -1.36
     sachant
    -1.34
     bisous
    -1.30
    Huile
    -1.30
     véhic
    -1.26
     coû
    -1.26
     dénon
    -1.26
     anunció
    -1.25
    deja
    -1.23
     kancel
    -1.21
    POSITIVE LOGITS
     just
    1.41
     as
    1.36
     now
    1.33
     instead
    1.29
    C
    1.28
     has
    1.27
    P
    1.23
     start
    1.20
     in
    1.18
     get
    1.18
    Activations Density 0.007%

    No Known Activations