© 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. 39333
    Prev
    Next
    INDEX
    Explanations

    optimally performed or performing

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

    sad panda, 🎶🇺, ✥╚, ☀️✨, greatest president, Gb/, sexual craving, derogatory

    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
    ಲಯ
    0.45
    ɺ
    0.43
     carbides
    0.43
    ｽ
    0.43
     teclas
    0.42
    debris
    0.42
    ом
    0.41
    tum
    0.41
    ব্লিউ
    0.41
    র্ত
    0.40
    POSITIVE LOGITS
     سر
    0.43
     Ches
    0.43
    валася
    0.42
     While
    0.41
     Chel
    0.40
     س
    0.39
     Pho
    0.38
     Shastri
    0.38
     بها
    0.38
     Choud
    0.38
    Activations Density 0.002%

    No Known Activations