© 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. 34-GEMMASCOPE-RES-131K
    7. 79025
    Prev
    Next
    INDEX
    Explanations

    slides

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

    The neuron fires on numeric tokens—that is, any standalone numbers or digit sequences.

    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
     Rica
    -0.85
    DONE
    -0.84
     تلویزیون
    -0.80
    (@"
    -0.80
    щихся
    -0.78
    addObject
    -0.78
     ulica
    -0.75
    amling
    -0.75
    BOLD
    -0.74
     DIAL
    -0.74
    POSITIVE LOGITS
     slides
    0.96
     loop
    0.90
     slide
    0.86
     pills
    0.83
     Single
    0.80
     davran
    0.78
     swipe
    0.77
     break
    0.77
     fling
    0.76
     адап
    0.72
    Activations Density 0.004%

    No Known Activations