© 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. 15925
    Prev
    Next
    INDEX
    Explanations

    starts of phrases or code snippets

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

    The neuron activates on numeric tokens or sequences of digits (i.e., any numbers or identifiers containing 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
     how
    -1.19
    ！(
    -0.96
     in
    -0.96
     retrofit
    -0.93
     reign
    -0.92
     ΤΟ
    -0.91
     uczniów
    -0.90
     rejuven
    -0.89
     can
    -0.88
     całego
    -0.88
    POSITIVE LOGITS
     []
    1.13
    lında
    1.11
     kHz
    1.11
    /−
    1.09
    സ്
    1.05
     aprobó
    1.05
    ;'
    1.05
    Também
    1.03
     murieron
    1.03
    Hvis
    1.02
    Activations Density 0.000%

    No Known Activations