© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9615
    Prev
    Next
    INDEX
    Explanations

    list separators and continuations

    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
     first
    -2.09
     it
    -1.94
    ྜ
    -1.92
     only
    -1.88
     with
    -1.79
     because
    -1.74
     two
    -1.70
     in
    -1.70
     there
    -1.69
     create
    -1.66
    POSITIVE LOGITS
     of
    2.30
    之色
    2.13
    艄
    2.09
    และ
    2.02
    Increased
    1.90
    蓐
    1.88
    noindent
    1.88
     insanely
    1.87
    (!__
    1.85
    increased
    1.82
    Activations Density 0.076%

    No Known Activations