© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10402
    Prev
    Next
    INDEX
    Explanations

    high quality standards

    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_10/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
     in
    -1.50
     with
    -1.48
    ())
    
    -1.42
    OREM
    -1.33
     or
    -1.30
    ggings
    -1.30
     assuming
    -1.29
    😐
    -1.29
    imageshack
    -1.27
    ])
    
    -1.25
    POSITIVE LOGITS
    from
    1.40
    MITTED
    1.37
    にしても
    1.36
     malgré
    1.34
    3
    1.33
    事は
    1.32
     никаких
    1.32
    ↵
    1.30
     بدون
    1.28
    楽しんで
    1.28
    Activations Density 0.034%

    No Known Activations