© 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. 22-GEMMASCOPE-RES-131K
    7. 65811
    Prev
    Next
    INDEX
    Explanations

    numbers, acronyms, or common beginnings

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

    The neuron strongly activates on tokens that mark positions in an ordered list—numbers and ordinals like “one,” “second,” “3,” “first,” “last,” etc.

    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
     which
    -1.14
     this
    -1.06
     when
    -1.03
     İyi
    -1.02
     Böyle
    -1.00
     TÉ
    -0.96
    このように
    -0.95
    RootElement
    -0.94
    ندان
    -0.94
    Often
    -0.93
    POSITIVE LOGITS
     would
    1.34
    但
    1.15
    จาก
    1.12
    如果
    1.10
     but
    1.09
    任何
    1.09
    hichever
    1.08
     anything
    1.07
    但是
    1.07
     assolutamente
    1.06
    Activations Density 0.010%

    No Known Activations