© 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. 71462
    Prev
    Next
    INDEX
    Explanations

    titles, places, and roles

    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
     Vertrieb
    -1.09
     for
    -1.06
     alip
    -0.92
     first
    -0.91
    ;
    -0.90
    ḇ
    -0.90
    رائه
    -0.88
     or
    -0.88
     olivat
    -0.88
     tertulis
    -0.87
    POSITIVE LOGITS
     hà
    1.17
    ₃
    1.13
    paravant
    1.13
     consejo
    1.10
     generell
    1.09
     historiador
    1.08
    προ
    1.08
    ₆
    1.06
     erforder
    1.05
     espé
    1.05
    Activations Density 0.218%

    No Known Activations