© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68305
    Prev
    Next
    INDEX
    Explanations

    physical dimensions and quantities

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

    The neuron activates on numeric tokens (digits and numbers, such as dates, measurements, quantities, 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_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
    yszer
    -1.05
    habited
    -0.94
    孽
    -0.93
    構築
    -0.91
    ował
    -0.91
     into
    -0.91
     online
    -0.90
    ICIO
    -0.90
    ꜜ
    -0.86
     appétit
    -0.86
    POSITIVE LOGITS
    acheteur
    1.02
    équilibre
    0.91
    extré
    0.90
    弱
    0.85
    écoute
    0.84
     杨
    0.84
    Termine
    0.84
    3
    0.83
    Salah
    0.81
    不及
    0.80
    Activations Density 0.015%

    No Known Activations