© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12322
    Prev
    Next
    INDEX
    Explanations

    <code>Container</code>, <code>frozen</code>, <code>stable</code>, <code>parent</code>, <code>6</code>, <code>if</code>, <code>Re</code>

    np_acts-logits-general · gemini-2.5-flash-lite

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    К
    0.87
    <h4>
    0.84
     uomini
    0.80
     rezultat
    0.79
     oğ
    0.79
    АР
    0.78
    "),
    0.78
    А
    0.78
    אם
    0.77
    Я
    0.77
    POSITIVE LOGITS
    ul
    0.96
    ant
    0.90
    te
    0.87
    ong
    0.87
    ou
    0.86
    ons
    0.85
    า
    0.85
    ale
    0.83
    ა
    0.82
    ipping
    0.80
    Activations Density 0.003%

    No Known Activations