© 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. 13961
    Prev
    Next
    INDEX
    Explanations

    conjunctions and logical operators

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

    The neuron strongly activates on numeric tokens (sequences of digits), i.e. it detects 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
    せっ
    -1.08
    
    -1.06
     gyrus
    -1.04
     тези
    -1.03
     pagamento
    -1.03
     and
    -1.03
     sò
    -1.03
    semver
    -1.02
     frapp
    -1.00
    μως
    -0.99
    POSITIVE LOGITS
     "
    1.41
     '
    1.19
     new
    1.07
     раньше
    1.04
     (
    1.03
     "";
    0.98
     thậm
    0.98
     sogar
    0.98
    用的
    0.97
     ("
    0.97
    Activations Density 0.022%

    No Known Activations