© 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. 22-GEMMASCOPE-RES-131K
    7. 73481
    Prev
    Next
    INDEX
    Explanations

    RTC streaming and calls

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

    The neuron is detecting numeric tokens—digits, version numbers, and other number‐containing strings.

    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
     we
    -1.30
     the
    -1.27
    ֩
    -1.13
     arbeitet
    -1.12
     where
    -1.11
    Nós
    -1.10
     about
    -1.05
     wypeł
    -1.05
     this
    -1.04
     our
    -1.04
    POSITIVE LOGITS
    ございます
    1.36
    👯
    1.31
    技术的
    1.25
    ilité
    1.23
     pasteur
    1.21
     YOGA
    1.21
     teknis
    1.18
     frac
    1.18
     bicarbon
    1.18
     streaming
    1.18
    Activations Density 0.043%

    No Known Activations