© 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. 40769
    Prev
    Next
    INDEX
    Explanations

    enrolled in

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

    The neuron selectively activates on mentions of enrollment (forms of “enroll,” “enrolled,” “enrolling,” 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_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
    รรม
    -1.77
    各样的
    -1.75
    嚒
    -1.72
    ⸢
    -1.70
    🫴
    -1.70
     chacun
    -1.69
    Literally
    -1.68
    ⇡
    -1.65
     laisser
    -1.63
    Saying
    -1.61
    POSITIVE LOGITS
     becomes
    1.93
    with
    1.92
     Organisator
    1.89
    欵
    1.88
     WITH
    1.84
    灕
    1.83
     This
    1.80
     Bemerkungen
    1.79
    ୈ
    1.77
     a
    1.73
    Activations Density 0.014%

    No Known Activations