© 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. 76856
    Prev
    Next
    INDEX
    Explanations

    picture/image source attribution

    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
    Courtesy
    -1.21
    courtesy
    -0.93
     Courtesy
    -0.91
     courtesy
    -0.77
    roleum
    -0.77
    Reprodução
    -0.76
    localized
    -0.76
     oferec
    -0.75
    orit
    -0.75
    promotion
    -0.75
    POSITIVE LOGITS
     supplied
    0.95
     Picture
    0.90
     Supplied
    0.85
     Chess
    0.83
     Images
    0.82
     Pictures
    0.81
    GRAPHS
    0.79
    dymo
    0.78
    bró
    0.78
    形象
    0.78
    Activations Density 0.024%

    No Known Activations