© 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. 38838
    Prev
    Next
    INDEX
    Explanations

    UI element dimensions

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

    The neuron activates on numeric literal tokens (numbers) in code or 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_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
     one
    -1.23
     these
    -1.23
     being
    -1.18
     the
    -1.15
     it
    -1.13
     From
    -1.12
     everything
    -1.12
     These
    -1.10
     is
    -1.09
     through
    -1.09
    POSITIVE LOGITS
     véhic
    1.08
    מעות
    1.05
     BEAUTIFUL
    0.99
     faciliter
    0.98
    หรับ
    0.98
    nesc
    0.97
     circons
    0.97
     continuer
    0.97
    养成
    0.96
    Handy
    0.96
    Activations Density 0.004%

    No Known Activations