© 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. 113813
    Prev
    Next
    INDEX
    Explanations

    pancreatic islets and geographic islands

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

    mentions of islets or islands, particularly in medical or biological contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     ewigen
    -1.33
     смысле
    -1.25
    __(
    -1.20
     occhi
    -1.17
     inevitable
    -1.16
    Ө
    -1.16
     sondern
    -1.14
    ologous
    -1.13
    2
    -1.13
    âtel
    -1.10
    POSITIVE LOGITS
     such
    1.40
    nagel
    1.27
    s
    1.24
    ὃ
    1.22
     know
    1.20
     могла
    1.20
    これだけ
    1.19
    。
    1.16
     такое
    1.14
     amongst
    1.11
    Activations Density 0.059%

    No Known Activations