© 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. 22-GEMMASCOPE-RES-131K
    4. 13486
    Prev
    Next
    INDEX
    Explanations

    value 1, 2, or 3

    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_22/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
    lover
    -0.96
    mení
    -0.94
     items
    -0.90
    ㅣ
    -0.89
     artykuł
    -0.86
    Ð
    -0.85
    ggars
    -0.85
     onStop
    -0.83
    \&
    -0.82
    <h2>
    -0.81
    POSITIVE LOGITS
     them
    0.99
     thereof
    0.94
    Ẫ
    0.94
     forza
    0.91
     corresponding
    0.90
     it
    0.88
    ledem
    0.88
     함께
    0.87
     соответству
    0.86
    ときは
    0.85
    Activations Density 0.013%

    No Known Activations