© 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. 34-GEMMASCOPE-RES-131K
    7. 99531
    Prev
    Next
    INDEX
    Explanations

    research paper

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

    The neuron selectively activates on numeric tokens (digits and numbers) wherever they appear 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_34/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
     رسد
    -1.17
     that
    -1.07
     made
    -1.05
    żenia
    -1.01
     prevents
    -0.99
     uzyskać
    -0.99
     connaît
    -0.98
     as
    -0.98
    ̬
    -0.97
     процес
    -0.96
    POSITIVE LOGITS
    ſelf
    1.24
    特に
    1.14
     alluring
    1.09
     glistening
    1.09
     !!!!
    1.07
    Additionally
    1.07
    
    1.07
    骉
    1.07
    Furthermore
    1.06
     ...
    1.05
    Activations Density 0.071%

    No Known Activations