© 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. 32707
    Prev
    Next
    INDEX
    Explanations

    comparing against others

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

    comparison and benchmarking

    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
     ইতিমধ্যে
    0.47
    ibilities
    0.45
    ở
    0.44
     помощью
    0.44
    lceil
    0.43
    useful
    0.43
    ivities
    0.43
     ಈಗಾಗಲೇ
    0.43
     ನೀವು
    0.43
    すでに
    0.42
    POSITIVE LOGITS
     anonym
    0.47
     benchmark
    0.46
     femenina
    0.45
     benchmarks
    0.45
     sammen
    0.44
     tillsammans
    0.44
     kvinn
    0.43
    勘
    0.43
     feminina
    0.42
     bersama
    0.42
    Activations Density 0.002%

    No Known Activations