© 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. 34-GEMMASCOPE-RES-131K
    7. 108776
    Prev
    Next
    INDEX
    Explanations

    French names and initials

    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
     delicado
    -0.93
    coloring
    -0.88
    fret
    -0.86
     Fotograf
    -0.84
    seater
    -0.83
    FactoryBean
    -0.82
    حدى
    -0.81
     ratón
    -0.81
     infierno
    -0.80
     agujas
    -0.80
    POSITIVE LOGITS
    Pretty
    0.93
     kara
    0.91
     Novgorod
    0.86
     parati
    0.85
     parenthesis
    0.82
     chromium
    0.81
    df
    0.81
     abus
    0.80
     deng
    0.79
     Pretty
    0.78
    Activations Density 0.301%

    No Known Activations