© 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. 66868
    Prev
    Next
    INDEX
    Explanations

    if I recall correctly

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

    This neuron spots numeric tokens, i.e. digits and numbers (years, counts, or other numeric expressions).

    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
    ῦ
    -1.15
    avadoc
    -1.14
    вои
    -1.11
     '-';
    -1.09
    此刻
    -0.99
     '/')
    -0.99
     four
    -0.97
    TRIBUN
    -0.96
    atum
    -0.96
    ïa
    -0.94
    POSITIVE LOGITS
     IIRC
    2.09
     iirc
    1.88
    確か
    1.39
    Beberapa
    1.22
     something
    1.14
     certain
    1.13
    之类的
    1.13
     some
    1.07
     (?)
    1.06
    (?
    1.06
    Activations Density 0.108%

    No Known Activations