© 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. 37939
    Prev
    Next
    INDEX
    Explanations

    not wanting to

    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
     السياسة
    -0.98
    ̀i
    -0.97
     ").
    -0.92
     зубов
    -0.87
    wot
    -0.85
     dépenses
    -0.84
     vinaigre
    -0.84
    UEGO
    -0.83
     vécu
    -0.82
    stoffen
    -0.82
    POSITIVE LOGITS
     spoke
    1.27
     say
    1.26
     moved
    1.23
     speak
    1.20
     move
    1.20
     says
    1.07
     particularly
    1.04
     speaks
    0.98
     moving
    0.98
     movement
    0.95
    Activations Density 0.019%

    No Known Activations