© 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. 190026
    Prev
    Next
    INDEX
    Explanations

    permitted by law

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

    embeddings, model, translate, surgery

    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
    a
    0.55
     lò
    0.50
     vibrant
    0.50
     bubbles
    0.49
     bubbling
    0.49
    the
    0.49
    да
    0.49
    bubbles
    0.48
    5
    0.48
    t
    0.48
    POSITIVE LOGITS
    netfx
    0.52
     त्रिपुरा
    0.50
    emon
    0.50
    ्यक्रम
    0.49
     वोल्टेज
    0.49
    咡
    0.48
     बल्लेबाज
    0.47
     Adverse
    0.46
     Вообще
    0.46
    omonas
    0.45
    Activations Density 0.005%

    No Known Activations