© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21667
    Prev
    Next
    INDEX
    Explanations

    Oregon institutions and locations

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

    The neuron fires on numeric tokens representing quantitative data (e.g., scores, measurements, or statistics).

    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
     freaking
    -2.72
    f
    -2.63
    e
    -2.56
     the
    -2.55
    ".
    -2.47
    v
    -2.42
     після
    -2.41
     cette
    -2.36
     этой
    -2.36
    *
    -2.33
    POSITIVE LOGITS
     of
    3.39
     për
    2.50
     silueta
    2.45
    闓
    2.28
     empowering
    2.27
    ✣
    2.25
     delgado
    2.17
     adulta
    2.16
     perfecta
    2.14
    𝓑
    2.14
    Activations Density 0.005%

    No Known Activations