© 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. 35437
    Prev
    Next
    INDEX
    Explanations

    digits and place values

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

    The neuron strongly activates on numbers and numeric literals (digits, numeric words, and 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_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
    sekret
    -1.09
     qualités
    -1.06
    dekor
    -1.04
    dosen
    -1.02
    gemar
    -1.02
     berken
    -1.01
     ejemplos
    -0.97
    verbs
    -0.96
    mended
    -0.96
     gospodar
    -0.96
    POSITIVE LOGITS
     from
    1.12
     because
    0.99
    构建
    0.98
     biggest
    0.98
     putting
    0.96
     लड़
    0.93
     placing
    0.92
    дян
    0.91
     nestled
    0.89
     since
    0.88
    Activations Density 0.010%

    No Known Activations