© 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. 42751
    Prev
    Next
    INDEX
    Explanations

    Listed below

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

    The neuron flags numeric literals in code or configuration (e.g. numbers appearing in XML attributes or parameters).

    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
    ">“
    -1.67
     fiabilidad
    -1.62
     prides
    -1.56
     manufactures
    -1.52
     помогает
    -1.52
     ines
    -1.52
     certificación
    -1.51
     conceptu
    -1.50
    pherds
    -1.50
    liegende
    -1.48
    POSITIVE LOGITS
     our
    2.42
     Offisielt
    1.72
     by
    1.71
     号
    1.71
     from
    1.63
    <th>
    1.63
    MAXN
    1.62
    日閲覧
    1.61
    dzić
    1.60
     three
    1.59
    Activations Density 0.002%

    No Known Activations