© 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. 10-GEMMASCOPE-RES-131K
    7. 72885
    Prev
    Next
    INDEX
    Explanations

    JVM Version or postcode

    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
    鋮
    -2.44
    摃
    -2.28
    捽
    -2.27
    which
    -2.23
    Ꮉ
    -2.11
     Which
    -2.08
    
    -1.99
    沇
    -1.99
    </strong>
    -1.88
    ꦒ
    -1.88
    POSITIVE LOGITS
    ING
    2.38
    }
    2.34
     they
    2.11
     большого
    1.98
     рекламы
    1.93
    棡
    1.93
    騭
    1.86
    侔
    1.84
     {
    1.80
    逦
    1.78
    Activations Density 0.010%

    No Known Activations