© 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. 223290
    Prev
    Next
    INDEX
    Explanations

    a followed by classes

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

    Download Google Adobe URL Sushi

    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
     Guille
    0.48
    am
    0.48
    Welcome
    0.47
    Mari
    0.47
     Sutton
    0.47
     wurden
    0.47
     Lucie
    0.46
    것
    0.46
    Са
    0.46
    Maria
    0.46
    POSITIVE LOGITS
    edes
    0.41
    गित
    0.40
     columnar
    0.40
     Anlagen
    0.40
     ارب
    0.39
    Initializer
    0.39
    ]=-
    0.39
    委員會
    0.39
    编辑器
    0.39
     친
    0.39
    Activations Density 0.000%

    No Known Activations