© 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. 41-GEMMASCOPE-2-RES-262K
    7. 25936
    Prev
    Next
    INDEX
    Explanations

    df.iloc or df.describe

    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_all/layer_41_width_262k_l0_big
    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
     তব
    0.41
     Constructs
    0.41
    </table>
    0.39
    建设
    0.39
     انجین
    0.39
    确定
    0.38
     설계
    0.38
     Jud
    0.38
    平凡
    0.38
     יה
    0.38
    POSITIVE LOGITS
     yellow
    0.40
    ≫
    0.39
     ell
    0.38
     connaître
    0.38
     coursework
    0.38
    blers
    0.38
    schein
    0.38
     dill
    0.37
    gcf
    0.37
    ritto
    0.37
    Activations Density 0.000%

    No Known Activations