© 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. 34-GEMMASCOPE-RES-131K
    7. 48611
    Prev
    Next
    INDEX
    Explanations

    designer from [place/brand]

    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
     AUSTIN
    -0.79
    Midwest
    -0.79
    𝖌
    -0.78
    ❓
    -0.77
     abitanti
    -0.76
    Victorian
    -0.76
    informe
    -0.75
    GEAR
    -0.74
     CENTURY
    -0.74
     GEAR
    -0.73
    POSITIVE LOGITS
     ethically
    0.92
     range
    0.87
     Collective
    0.84
     Byron
    0.83
    gyp
    0.83
     EOF
    0.82
    Range
    0.75
    \}_{
    0.75
     ranges
    0.75
     Resort
    0.75
    Activations Density 0.027%

    No Known Activations