© 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. 45075
    Prev
    Next
    INDEX
    Explanations

    two and subsequent nouns

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

    The neuron activates strongly on the word “two.”

    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
     you
    -2.23
     it
    -2.09
    ↵↵
    -1.73
     Privacidad
    -1.70
    ності
    -1.69
     Mijn
    -1.64
     главным
    -1.64
    ;
    -1.59
    ophageal
    -1.57
    {
    -1.57
    POSITIVE LOGITS
    卨
    1.97
    「
    1.82
    “
    1.66
    𝟚
    1.65
    liehen
    1.59
    ALLENGES
    1.59
     are
    1.53
    在我
    1.52
     „
    1.52
    された
    1.51
    Activations Density 0.011%

    No Known Activations