© 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. 2886
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific citations

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

    The neuron strongly activates on multi‐digit numeric tokens (long sequences of digits).

    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
    bestimm
    -1.15
     only
    -1.14
    jangkau
    -1.09
     rosca
    -1.09
    lenovo
    -1.08
    uangan
    -1.06
    dekat
    -1.05
     almuerzo
    -1.05
    alatan
    -1.04
     nyata
    -1.03
    POSITIVE LOGITS
    0
    1.29
    th
    1.22
    ↵↵↵
    1.20
    c
    1.09
    1.04
    ag
    1.03
    b
    1.03
        
    1.02
    co
    1.01
    Ibid
    1.01
    Activations Density 0.057%

    No Known Activations