© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11309
    Prev
    Next
    INDEX
    Explanations

    countries and citizenship

    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_31_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
    )}-\
    0.52
    hebung
    0.47
    сель
    0.45
    }$&$
    0.45
    ப்ச
    0.44
    ത്തും
    0.43
    стки
    0.43
    斯的
    0.42
    мен
    0.42
    вере
    0.42
    POSITIVE LOGITS
     wanna
    0.44
     United
    0.43
     senators
    0.41
    '
    0.41
    要想
    0.40
     accredited
    0.40
    ariously
    0.39
     Pestic
    0.39
     reputable
    0.39
     Nationality
    0.39
    Activations Density 0.002%

    No Known Activations