© 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. 39695
    Prev
    Next
    INDEX
    Explanations

    last update, Investor Committee, Now that

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

    language prevention and protection

    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
    可靠
    0.55
     સલા
    0.54
     Сте
    0.52
    pessoa
    0.52
     respiratoires
    0.52
     бош
    0.50
    湋
    0.50
     потребу
    0.49
     મોટા
    0.49
    avnom
    0.49
    POSITIVE LOGITS
     punished
    0.50
    呢
    0.49
     imag
    0.47
     let
    0.46
     遊ん
    0.46
     didn
    0.46
     }
    0.46
     ise
    0.45
     BLOG
    0.45
     had
    0.44
    Activations Density 0.000%

    No Known Activations