© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112528
    Prev
    Next
    INDEX
    Explanations

    question and answer

    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
     länder
    -1.67
     peixes
    -1.48
    
    -1.45
     sapatos
    -1.41
    珅
    -1.41
     avions
    -1.39
     konkret
    -1.37
     offrir
    -1.34
     rendimiento
    -1.31
     restant
    -1.30
    POSITIVE LOGITS
     after
    1.45
    beforeEach
    1.32
     one
    1.30
     robić
    1.28
    жении
    1.27
     they
    1.27
     zaczą
    1.27
     more
    1.26
     trying
    1.26
    了很多
    1.25
    Activations Density 0.019%

    No Known Activations