© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13592
    Prev
    Next
    INDEX
    Explanations

    one or the other

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

    The neuron fires on occurrences of the word “other.”

    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>
    -1.73
     and
    -1.72
     alojamientos
    -1.69
     семь
    -1.68
     برش
    -1.65
    那样
    -1.62
     peores
    -1.62
    ’:
    -1.59
     россий
    -1.59
    ?"
    -1.56
    POSITIVE LOGITS
     When
    1.88
     There
    1.76
     become
    1.73
     Ultimately
    1.63
    рите
    1.63
    𝄆
    1.61
     Not
    1.61
     Another
    1.58
    "
    1.58
     This
    1.55
    Activations Density 0.008%

    No Known Activations