© 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. 71909
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    ,
    -1.96
     regresó
    -1.88
     anunció
    -1.69
     pousada
    -1.67
     необхід
    -1.64
    寕
    -1.63
     visitar
    -1.62
     lanzó
    -1.60
     confirmó
    -1.60
    lampen
    -1.59
    POSITIVE LOGITS
     also
    1.88
     who
    1.81
    \
    1.71
     
    1.68
     také
    1.68
     nehmen
    1.67
     như
    1.59
     \
    1.57
     którego
    1.55
     his
    1.50
    Activations Density 0.000%

    No Known Activations