© 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. 73079
    Prev
    Next
    INDEX
    Explanations

    "IN" followed by a word

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

    This neuron fires on the standalone uppercase token “IN.”

    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
    R
    -4.16
    to
    -3.72
    0
    -3.55
    F
    -3.50
    A
    -3.48
    W
    -3.34
    -
    -3.34
    E
    -3.22
    L
    -3.20
    C
    -3.17
    POSITIVE LOGITS
    ⎆
    3.06
    ⃙
    2.97
    튿
    2.91
    ſtra
    2.88
    潆
    2.83
     esquí
    2.77
    
    2.75
    AdvEx
    2.73
    reonine
    2.72
    嵎
    2.72
    Activations Density 0.010%

    No Known Activations