© 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. 10-GEMMASCOPE-RES-131K
    7. 41223
    Prev
    Next
    INDEX
    Explanations

    percentages followed by the

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

    The neuron fires on numeric tokens, i.e. standalone numbers 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
    ⇹
    -1.94
    撂
    -1.88
     probablement
    -1.84
     quantidade
    -1.83
    putan
    -1.81
    悄悄
    -1.80
    看他
    -1.73
     ejecuta
    -1.72
    ሒ
    -1.68
     
    -1.67
    POSITIVE LOGITS
     ambayo
    1.98
    '
    1.97
     that
    1.97
    啊啊
    1.90
    ),
    1.80
     yako
    1.80
     who
    1.80
     sizeable
    1.77
     outstanding
    1.76
     ambao
    1.74
    Activations Density 0.020%

    No Known Activations