© 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. 40711
    Prev
    Next
    INDEX
    Explanations

    new to a language

    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
     brinde
    -1.38
    関わ
    -1.27
     WASH
    -1.25
     devenus
    -1.23
     again
    -1.22
     imagens
    -1.21
     MotionEvent
    -1.16
    るか
    -1.16
     verhind
    -1.16
     exemples
    -1.16
    POSITIVE LOGITS
     are
    1.77
    一些
    1.58
     what
    1.55
     những
    1.42
     things
    1.40
     type
    1.38
     those
    1.38
    );
    1.36
     would
    1.35
    那些
    1.35
    Activations Density 0.217%

    No Known Activations