© 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. 10-GEMMASCOPE-RES-131K
    7. 73243
    Prev
    Next
    INDEX
    Explanations

    HTML attribute assignments

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

    The neuron responds to numeric tokens (numbers) embedded in code or markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Kleur
    -1.33
    Materiaal
    -1.30
    )
    -1.29
    เยอะ
    -1.25
     was
    -1.20
    䊊
    -1.20
    はじめまして
    -1.17
    艽
    -1.16
    Conclusie
    -1.16
    Kondisi
    -1.15
    POSITIVE LOGITS
     about
    1.50
     =
    1.40
     вслед
    1.37
    侭
    1.27
     .
    1.26
    дают
    1.21
     ...
    1.16
     They
    1.15
     έχουν
    1.14
    acea
    1.13
    Activations Density 0.005%

    No Known Activations