© 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. 33095
    Prev
    Next
    INDEX
    Explanations

    in detention centers or cells

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

    safety gear

    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
     అంశ
    0.51
     некоторы
    0.46
    ради
    0.46
    робнее
    0.44
     нами
    0.43
    िफिशियल
    0.43
     законом
    0.42
    麸
    0.41
    我们需要
    0.40
     Реа
    0.39
    POSITIVE LOGITS
     spacious
    0.46
     chairs
    0.45
     těch
    0.45
     inhabiting
    0.44
     stunned
    0.44
     położ
    0.43
     Ontario
    0.42
     southeast
    0.42
     décrit
    0.42
     bezpośred
    0.42
    Activations Density 0.001%

    No Known Activations