© 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. 34-GEMMASCOPE-RES-131K
    7. 32604
    Prev
    Next
    INDEX
    Explanations

    names starting with certain prefixes

    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_34/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
    Leírás
    -1.23
    SEGUIR
    -1.20
     atti
    -1.20
    ליון
    -1.20
     valla
    -1.18
    Комментарии
    -1.17
     sudadera
    -1.13
    หว่าง
    -1.11
    ictwa
    -1.11
    ppuden
    -1.11
    POSITIVE LOGITS
     familières
    1.27
    "
    1.21
     marquées
    1.21
    (
    1.20
     gratuits
    1.14
     detuvo
    1.13
     noires
    1.12
     colorés
    1.12
    perative
    1.11
    を行います
    1.11
    Activations Density 0.307%

    No Known Activations