© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 13810
    Prev
    Next
    INDEX
    Explanations

    genre, race, ethnicity, shorthand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ø
    0.48
    ant
    0.44
     Defin
    0.42
     Зна
    0.40
     describe
    0.40
     significant
    0.40
     contains
    0.39
     Description
    0.39
     Опреде
    0.39
    nat
    0.39
    POSITIVE LOGITS
    懇
    0.44
    ੁੱ
    0.41
     felonies
    0.39
     políticos
    0.38
    濒
    0.38
    랗
    0.37
    गेड
    0.37
    сійскай
    0.37
    homotopic
    0.37
    inairement
    0.36
    Activations Density 0.000%

    No Known Activations