© 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. 8813
    Prev
    Next
    INDEX
    Explanations

    foreign, finance, sports, rankings

    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
    Ge
    0.52
    ↵↵
    0.52
    Quan
    0.52
    \
    0.52
    Em
    0.50
    >
    0.50
    cie
    0.50
    -
    0.48
    Sw
    0.48
     Gris
    0.47
    POSITIVE LOGITS
    𝚜
    0.54
    𝓈
    0.50
     Фургала
    0.47
     സമൂഹ
    0.47
     постоянно
    0.46
     втор
    0.46
     упро
    0.46
     पुरंदरे
    0.45
     сфор
    0.45
     Фургал
    0.44
    Activations Density 0.002%

    No Known Activations