© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66954
    Prev
    Next
    INDEX
    Explanations

    Q and A

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

    The neuron is strongly activated by sequences of digits used as list or section numbering (e.g. “8 8 9 IV,” “889 V,” “8 9 1 VII,” 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
     from
    -1.58
     which
    -1.58
     in
    -1.18
     both
    -1.16
     as
    -1.13
     those
    -1.13
     of
    -1.08
     at
    -1.07
     while
    -1.05
     dozens
    -1.05
    POSITIVE LOGITS
     dreary
    1.06
     focuses
    1.05
     horrifying
    1.02
     unn
    1.01
    ふわ
    1.01
    פא
    1.00
     horrid
    0.99
     discusses
    0.99
     FAQs
    0.99
    THEY
    0.97
    Activations Density 0.001%

    No Known Activations