© 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. 13909
    Prev
    Next
    INDEX
    Explanations

    canadian soccer league

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

    The neuron activates on numeric tokens (years, scores, measurements, counts, etc.), i.e. it finds numbers.

    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
    苦笑
    -0.95
    catchError
    -0.95
     bailando
    -0.89
    してしまった
    -0.88
    しつつ
    -0.87
     nordrhein
    -0.86
    咎
    -0.86
     abuso
    -0.85
    ใหญ
    -0.85
    痺
    -0.84
    POSITIVE LOGITS
    你们
    1.20
    zeniem
    1.16
     данный
    1.13
     declaración
    1.12
    在这
    1.11
    /**
    1.10
     данной
    1.09
     Sloveniji
    1.06
    onekana
    1.05
    也很
    1.05
    Activations Density 0.011%

    No Known Activations