© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94111
    Prev
    Next
    INDEX
    Explanations

    version numbers and names

    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_34/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
     on
    -0.80
     their
    -0.79
    اوم
    -0.79
    حاب
    -0.79
    xicity
    -0.79
     nearly
    -0.79
     only
    -0.78
     merely
    -0.77
     mainly
    -0.76
     mostly
    -0.75
    POSITIVE LOGITS
    <h3>
    1.11
     entraîner
    0.95
    Ещё
    0.91
     nedeniyle
    0.90
    <h4>
    0.90
    jay
    0.88
    borderFill
    0.87
     alté
    0.85
    <h2>
    0.85
     grotte
    0.82
    Activations Density 0.002%

    No Known Activations