© 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. 10-GEMMASCOPE-RES-131K
    4. 103137
    Prev
    Next
    INDEX
    Explanations

    Apple found

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

    This neuron activates on standalone numeric tokens (e.g. counts or statistics) appearing in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    er
    -2.70
    ?"
    -2.67
     was
    -2.55
     temprano
    -2.19
     prides
    -2.16
     alcune
    -2.14
     pursues
    -2.14
    漚
    -2.13
    在她
    -2.13
    化的
    -2.11
    POSITIVE LOGITS
    ).
    3.69
    ↵
    2.77
    the
    2.73
    ),
    2.64
    ࿙
    2.44
    你看
    2.44
    {
    2.34
    .
    2.22
     immeasurable
    2.05
    ?
    2.05
    Activations Density 0.001%

    No Known Activations