© 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. 128441
    Prev
    Next
    INDEX
    Explanations

    words starting with "Co"

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

    The neuron strongly activates on tokens ending with the letter‐pair “to” (including Latin “sto,” “Co,” or the Cyrillic “что”).

    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
    U
    -3.08
    an
    -2.86
    A
    -2.72
    r
    -2.64
    8
    -2.61
    ان
    -2.56
    D
    -2.55
     of
    -2.48
    B
    -2.41
    also
    -2.34
    POSITIVE LOGITS
    嘥
    2.38
    を選び
    2.33
    錚
    2.31
    </em>
    2.19
     orienta
    2.11
    馴
    2.03
    ༴
    2.02
    苤
    2.02
     entusi
    2.00
    椟
    1.96
    Activations Density 0.001%

    No Known Activations