© 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. 35194
    Prev
    Next
    INDEX
    Explanations

    blocks/, defaultMessage, orderDate, increment, nelmio

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

    The neuron activates on numeric tokens—both integers and decimal numbers—wherever they appear 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_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
     כל
    -0.92
     never
    -0.91
     comunicação
    -0.91
     как
    -0.90
    '));
    -0.88
     Each
    -0.88
     divulgação
    -0.88
     kosten
    -0.86
     likes
    -0.85
     лишь
    -0.85
    POSITIVE LOGITS
    iertas
    1.16
     decoracion
    1.15
     acides
    1.11
     मोबाइल
    1.06
     pijama
    1.04
    焢
    1.04
    Ār
    1.02
    ПРО
    1.02
    destin
    1.02
     cheminée
    1.01
    Activations Density 0.005%

    No Known Activations