© 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. 112781
    Prev
    Next
    INDEX
    Explanations

    sustainable development and policy

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

    commas following items in lists, especially when followed by "and".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric tokens, especially decimal numbers and other quantitative values.

    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
     but
    -1.80
    either
    -1.72
    ệu
    -1.71
    bisous
    -1.70
     benefícios
    -1.69
    Efter
    -1.66
    Either
    -1.66
    cinq
    -1.65
    eight
    -1.64
     Infór
    -1.64
    POSITIVE LOGITS
     of
    1.88
     
    1.78
     –
    1.55
     get
    1.51
     and
    1.49
    <em>
    1.37
    ísica
    1.37
     التالي
    1.35
     would
    1.33
    步行
    1.33
    Activations Density 0.114%

    No Known Activations