© 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. 45147
    Prev
    Next
    INDEX
    Explanations

    local URLs and code snippets

    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
     at
    -1.80
     by
    -1.71
    This
    -1.62
     embodies
    -1.59
     through
    -1.55
     until
    -1.55
     foram
    -1.52
     keadaan
    -1.52
     in
    -1.52
     celebrado
    -1.52
    POSITIVE LOGITS
    小弟
    1.97
     داشتم
    1.92
    2
    1.89
    说到
    1.82
    或者
    1.82
    ῞
    1.79
    3
    1.77
     خونه
    1.76
     sauvages
    1.73
    ();
    1.71
    Activations Density 0.001%

    No Known Activations