© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91216
    Prev
    Next
    INDEX
    Explanations

    old followed by proper names

    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
    長い
    -0.98
     geomé
    -0.92
    長く
    -0.88
    etano
    -0.85
     básico
    -0.81
     ทรง
    -0.81
    politician
    -0.81
     ocorreu
    -0.80
     ensayo
    -0.79
    いただきました
    -0.79
    POSITIVE LOGITS
     fashioned
    2.39
    fashioned
    1.69
     adage
    1.49
    new
    1.21
    timer
    1.13
    school
    1.11
     Trafford
    1.08
    style
    1.07
     testament
    1.07
    fashion
    1.04
    Activations Density 0.022%

    No Known Activations