© 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. 197728
    Prev
    Next
    INDEX
    Explanations

    stunning combination

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

    modelthis remain model Weaver greet

    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
    ی
    0.47
     recogida
    0.46
    heda
    0.45
    ы
    0.45
    夫
    0.44
    sby
    0.43
    翼
    0.42
    ἵ
    0.42
    价值
    0.42
    asos
    0.41
    POSITIVE LOGITS
    PARAM
    0.52
    ")]
    0.49
     הת
    0.48
     роботи
    0.48
     occupying
    0.47
     filling
    0.47
     ‬
    0.46
     ആൻ
    0.45
     honoring
    0.45
     Technologies
    0.45
    Activations Density 0.000%

    No Known Activations