© 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. 181361
    Prev
    Next
    INDEX
    Explanations

    phrase how you `phrase`

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

    technical, health, and belief concepts

    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
     скажу
    0.47
     malfunction
    0.45
     deformity
    0.44
    Pixmap
    0.43
    μου
    0.43
     Gabriele
    0.43
    嘩
    0.42
     Scarlet
    0.41
     Berber
    0.41
     peritoneum
    0.41
    POSITIVE LOGITS
    ızlı
    0.56
    🚆
    0.54
    纽约
    0.50
     تحقيق
    0.50
     çalışan
    0.49
     İst
    0.48
     tööt
    0.48
    的服务
    0.47
    வற்ற
    0.47
     möjlig
    0.47
    Activations Density 0.000%

    No Known Activations