© 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. 13004
    Prev
    Next
    INDEX
    Explanations

    historical figures and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Ỷ
    -1.26
    ัณฑ์
    -1.25
     นัก
    -1.20
    luiting
    -1.20
    oznam
    -1.14
    емым
    -1.14
     音乐
    -1.13
    ︷
    -1.13
     comentários
    -1.13
    wochen
    -1.13
    POSITIVE LOGITS
    <bos>
    1.38
     two
    1.37
     any
    1.30
     many
    1.24
     ruolo
    1.19
     different
    1.14
     other
    1.13
     Many
    1.09
     great
    1.07
     more
    1.05
    Activations Density 0.061%

    No Known Activations