© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68587
    Prev
    Next
    INDEX
    Explanations

    clicking or pressing buttons

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

    The neuron detects numeric tokens (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
     undergone
    -0.99
    isser
    -0.98
    私が
    -0.97
     постав
    -0.96
    ก
    -0.94
    حت
    -0.93
    ються
    -0.93
     every
    -0.93
    esis
    -0.92
    ⇔
    -0.92
    POSITIVE LOGITS
     to
    2.34
    เพื่อ
    1.16
    Expecting
    1.12
     resulted
    1.06
     resulting
    1.05
     לקבל
    1.05
    figurine
    1.05
    portraits
    1.04
     then
    1.03
     result
    1.02
    Activations Density 0.165%

    No Known Activations