© 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. 71090
    Prev
    Next
    INDEX
    Explanations

    locations after in

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

    The neuron activates on numeric tokens or digit‐based figures 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
     a
    -1.17
    NECTIONS
    -1.13
    Bisous
    -1.11
     two
    -1.10
     something
    -1.09
     any
    -1.09
    ܜ
    -1.09
    
    -1.09
    ссию
    -1.09
    اعر
    -1.08
    POSITIVE LOGITS
     közül
    1.16
     like
    1.07
     such
    1.05
     lainnya
    1.04
     of
    1.00
    JHEP
    0.99
    ようだ
    0.97
    in
    0.97
    gyp
    0.97
     других
    0.96
    Activations Density 0.080%

    No Known Activations