© 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. 93043
    Prev
    Next
    INDEX
    Explanations

    Google API projects

    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
    Bh
    -0.90
    Breast
    -0.90
     Bh
    -0.83
     Breast
    -0.83
     iOS
    -0.81
    ченной
    -0.80
     breast
    -0.79
     ఒ
    -0.75
    breast
    -0.75
     Doctor
    -0.74
    POSITIVE LOGITS
    zones
    0.80
    kø
    0.77
     projects
    0.77
     پروژه
    0.77
    ljeno
    0.73
     operar
    0.73
     Hereford
    0.72
     digger
    0.71
    ຊ
    0.71
     zones
    0.71
    Activations Density 0.027%

    No Known Activations