© 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. 111676
    Prev
    Next
    INDEX
    Explanations

    items, lists, and structured data

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

    single-digit numbers, especially when they appear in lists, sequences, or structured data like code, tables, or technical documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ’
    -1.77
    _
    -1.64
     current
    -1.62
    .}(
    -1.55
     dagens
    -1.52
     Qaeda
    -1.50
     already
    -1.48
     hjemmes
    -1.44
    .
    -1.42
     mineures
    -1.41
    POSITIVE LOGITS
    ztes
    1.64
     metropolitana
    1.56
    !");
    1.55
    枚目
    1.52
    游戏亮点
    1.52
    vaná
    1.47
     molesta
    1.47
     hubieran
    1.45
     worin
    1.43
     renuncia
    1.42
    Activations Density 0.081%

    No Known Activations