© 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. 77499
    Prev
    Next
    INDEX
    Explanations

    Matt Creampies Hugh

    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
     richness
    -0.78
     could
    -0.77
    olstein
    -0.76
     passengers
    -0.75
     suffering
    -0.73
     philosophers
    -0.73
    seu
    -0.72
    × 
    -0.71
     Gegen
    -0.71
    emus
    -0.71
    POSITIVE LOGITS
     angezeigt
    0.81
    liegenden
    0.81
    godic
    0.81
    modified
    0.81
     Foreign
    0.79
    дые
    0.78
    zzi
    0.78
    Variable
    0.77
    ający
    0.76
    proud
    0.76
    Activations Density 0.010%

    No Known Activations