© 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. 34-GEMMASCOPE-RES-131K
    7. 76594
    Prev
    Next
    INDEX
    Explanations

    setting up mathematical definitions

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

    The neuron detects terminology and context related to epidemiological models of disease spread.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     isim
    -1.10
     calcetines
    -0.96
     semblent
    -0.96
     mengapa
    -0.96
     твои
    -0.93
     botines
    -0.92
     parachoque
    -0.92
    他也
    -0.91
     sudad
    -0.91
     подтвер
    -0.90
    POSITIVE LOGITS
     let
    3.44
     Let
    2.92
    Let
    2.86
     consider
    2.77
     Consider
    2.44
     suppose
    2.42
     assume
    2.23
    Consider
    2.20
     Suppose
    2.14
    Suppose
    2.05
    Activations Density 0.056%

    No Known Activations