© 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. 38452
    Prev
    Next
    INDEX
    Explanations

    ability or possibility

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

    This neuron primarily fires on occurrences of the modal verb “can” (and similar ability 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
    うわ
    -2.11
    えっ
    -2.06
    さぁ
    -1.92
    久し
    -1.91
    つづく
    -1.81
    もうすぐ
    -1.80
    ほら
    -1.78
    を行い
    -1.76
    だいぶ
    -1.75
    の為
    -1.74
    POSITIVE LOGITS
     to
    2.41
     from
    2.13
     on
    1.90
    os
    1.66
     with
    1.52
     get
    1.52
     before
    1.51
    p
    1.46
     during
    1.46
     for
    1.45
    Activations Density 0.011%

    No Known Activations