© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22206
    Prev
    Next
    INDEX
    Explanations

    servlet and Path in code

    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
    『
    -1.59
     =
    -1.59
    蹀
    -1.41
     Hauptmann
    -1.40
     lanterna
    -1.31
     russa
    -1.30
     『
    -1.30
     coreana
    -1.28
     corda
    -1.27
     sportivo
    -1.27
    POSITIVE LOGITS
     of
    2.28
     at
    1.76
     for
    1.57
     it
    1.55
     but
    1.46
     in
    1.44
     mittelalter
    1.43
    を目指
    1.39
    満た
    1.35
    sities
    1.34
    Activations Density 0.001%

    No Known Activations