© 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. 222366
    Prev
    Next
    INDEX
    Explanations

    older gods

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

    Traditional artistic, Rodriguez actually, access to

    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
    ة
    0.47
    有一個
    0.47
     geschlossen
    0.46
    군의
    0.46
     gerektiğini
    0.45
    闔
    0.45
    CLOSED
    0.43
     onu
    0.43
     ребенок
    0.42
    唓
    0.42
    POSITIVE LOGITS
    amera
    0.47
     Pir
    0.46
     Plays
    0.46
    orse
    0.45
     Casting
    0.45
    airi
    0.43
    ীরা
    0.43
     Transformations
    0.42
     देवी
    0.42
    "
    0.42
    Activations Density 0.000%

    No Known Activations