© 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. 10-GEMMASCOPE-RES-131K
    7. 101670
    Prev
    Next
    INDEX
    Explanations

    appears and related concepts

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

    This neuron detects occurrences of the verb “appear” (and its inflected forms) across languages.

    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
    塒
    -2.31
     neb
    -2.06
    <td>
    -1.95
    ма
    -1.94
     monstru
    -1.92
     fusil
    -1.90
     Reſ
    -1.88
    go
    -1.88
    馘
    -1.86
    based
    -1.81
    POSITIVE LOGITS
    ’
    2.55
    </strong>
    2.25
    t
    2.06
     –
    2.03
     использованием
    1.88
     учетом
    1.81
     uncomfortable
    1.80
     необходимость
    1.77
     bzw
    1.72
     tbh
    1.71
    Activations Density 0.003%

    No Known Activations