© 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. 10-GEMMASCOPE-RES-131K
    7. 113762
    Prev
    Next
    INDEX
    Explanations

    `.ag` or numbers

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

    The neuron predominantly activates on standalone numeric tokens (digits or multi‐digit strings) such as case numbers, page or section references, and phone‐number fragments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     offrir
    -1.99
     télécharger
    -1.94
     réserver
    -1.91
     diriger
    -1.87
     préstamos
    -1.86
     parcourir
    -1.85
     compléter
    -1.80
     terminer
    -1.80
    给他们
    -1.79
     !!!!
    -1.77
    POSITIVE LOGITS
     on
    2.33
     of
    2.31
     in
    2.30
     with
    2.23
     some
    2.17
     one
    2.06
     two
    1.98
     without
    1.98
     an
    1.95
     at
    1.93
    Activations Density 0.001%

    No Known Activations