© 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. 16-GEMMASCOPE-2-RES-262K
    7. 35144
    Prev
    Next
    INDEX
    Explanations

    tacos

    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_16_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
    u
    0.88
     څر
    0.82
    ړئ
    0.81
     سپورټ
    0.79
     espaços
    0.77
     بُک
    0.77
     техники
    0.77
     کتاب
    0.76
    tDBOutput
    0.75
    پيديا
    0.75
    POSITIVE LOGITS
    ↵↵
    1.09
    ’
    0.89
    3
    0.89
     on
    0.83
     that
    0.80
    '
    0.79
     by
    0.78
    ق
    0.78
    }
    0.76
    -
    0.75
    Activations Density 0.002%

    No Known Activations