© 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. 65171
    Prev
    Next
    INDEX
    Explanations

    sole original member

    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
     a
    -0.91
    ignants
    -0.90
    श्लेषण
    -0.75
    гр
    -0.74
    ulant
    -0.72
    窖
    -0.72
    ","
    -0.71
    Rigidbody
    -0.71
    subfigure
    -0.70
     <",
    -0.69
    POSITIVE LOGITS
     един
    4.69
    唯一
    4.09
     única
    3.44
     único
    3.31
     sole
    3.11
    唯一的
    2.97
     únicos
    2.81
     eneste
    2.81
     تنها
    2.80
     jedin
    2.80
    Activations Density 0.140%

    No Known Activations