© 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. 10-GEMMASCOPE-RES-131K
    7. 103342
    Prev
    Next
    INDEX
    Explanations

    i3, gns3, rm3, nfs3

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

    the digit "3" in technical or code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on standalone numeric tokens (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_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
     providing
    -2.66
     thwart
    -2.55
    ثمان
    -2.39
     vehemently
    -2.39
     ostensibly
    -2.36
     bolster
    -2.33
    ción
    -2.31
     revital
    -2.30
     seasoned
    -2.27
     three
    -2.25
    POSITIVE LOGITS
     '-
    3.03
     alguns
    2.56
    rd
    2.30
    s
    2.25
     !!!!
    2.14
    
    2.11
    3
    2.11
    KE
    2.03
     '/
    2.00
    ENTO
    1.98
    Activations Density 0.078%

    No Known Activations