© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92770
    Prev
    Next
    INDEX
    Explanations

    Javascript code blocks

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

    The neuron is keyed to spotting numeric literals (digits or numbers) in the 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_34/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
     ā
    -0.84
    ändige
    -0.83
    энер
    -0.82
    齧
    -0.76
     uur
    -0.76
    леты
    -0.75
     panas
    -0.74
     waar
    -0.74
    ума
    -0.72
    🧫
    -0.72
    POSITIVE LOGITS
    нологі
    0.85
     дори
    0.85
    いが
    0.83
    ală
    0.82
    ฒ
    0.81
    츄
    0.79
     desgracia
    0.79
     gier
    0.77
    équipements
    0.77
    (“
    0.77
    Activations Density 0.023%

    No Known Activations