© 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. 30494
    Prev
    Next
    INDEX
    Explanations

    as classifications

    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
    細い
    -1.09
    どこに
    -1.08
    絶妙
    -1.08
    可谓
    -1.05
    色んな
    -1.05
     partiellement
    -0.96
    榇
    -0.96
    可以说是
    -0.94
    すっきり
    -0.93
    versammlung
    -0.91
    POSITIVE LOGITS
     only
    1.48
     solely
    1.30
     crazy
    1.23
     hanya
    1.23
     sadece
    1.21
     ONLY
    1.20
     somehow
    1.18
     yalnızca
    1.18
     something
    1.17
     csak
    1.15
    Activations Density 0.075%

    No Known Activations