© 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. 11063
    Prev
    Next
    INDEX
    Explanations

    finished, discarded, choices, laughter

    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
    0.55
    era
    0.51
    com
    0.50
    4
    0.50
    1
    0.48
    ini
    0.48
    drop
    0.47
    6
    0.47
    3
    0.46
    inga
    0.46
    POSITIVE LOGITS
    賂
    0.55
    㭂
    0.51
    ادة
    0.47
    预算
    0.47
    )};
    0.46
    빔
    0.46
     الط
    0.46
    北京市
    0.45
    解决了
    0.45
    的能力
    0.45
    Activations Density 0.003%

    No Known Activations