© 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. 106775
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
     L
    -1.47
     D
    -1.37
     M
    -1.36
     F
    -1.36
     one
    -1.34
     N
    -1.30
     discernible
    -1.30
     T
    -1.30
     S
    -1.30
     on
    -1.26
    POSITIVE LOGITS
    ↵↵↵
    1.55
    ↵↵
    1.52
    鹪
    1.44
    🫴
    1.40
     árvores
    1.39
     スリーブ
    1.36
    ↵↵↵↵↵↵↵
    1.34
     espécies
    1.34
     菇
    1.33
     plusieurs
    1.30
    Activations Density 0.061%

    No Known Activations