© 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. 80984
    Prev
    Next
    INDEX
    Explanations

    preliminary steps

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

    hold each

    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
    㳻
    0.52
     Миха
    0.49
    オレンジ
    0.48
     кристал
    0.45
    睢
    0.45
    ноп
    0.45
    жди
    0.45
     Communism
    0.45
     стек
    0.45
    |<\
    0.44
    POSITIVE LOGITS
    aut
    0.54
    ip
    0.52
    ut
    0.51
    zhihu
    0.49
    मण
    0.49
    ai
    0.47
    HR
    0.47
    ampak
    0.46
     politik
    0.46
    produk
    0.46
    Activations Density 0.000%

    No Known Activations