© 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. 200827
    Prev
    Next
    INDEX
    Explanations

    items large and small

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

    device startups

    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
    ilta
    0.46
     развивается
    0.46
     दिश
    0.45
    嫦
    0.45
    发挥
    0.43
    ⵔ
    0.42
     मश
    0.42
    ịnh
    0.42
    ],”
    0.42
    anjem
    0.42
    POSITIVE LOGITS
    ಗಳನ್ನು
    0.58
     pretended
    0.45
     duality
    0.44
    linux
    0.44
     pretzel
    0.43
     system
    0.43
     theorem
    0.43
     prolet
    0.43
    귤
    0.42
    ಗಳ
    0.42
    Activations Density 0.000%

    No Known Activations