© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 59472
    Prev
    Next
    INDEX
    Explanations

    relative to horizontal layout

    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
    hibit
    0.44
     dawned
    0.39
    ائیگی
    0.38
    ifico
    0.37
    提及
    0.37
     shield
    0.37
     movieId
    0.37
    盾
    0.37
     dring
    0.37
     preferências
    0.37
    POSITIVE LOGITS
    Geme
    0.42
     напо
    0.41
    ekte
    0.40
     Holman
    0.38
     לש
    0.38
    Nell
    0.38
     Sutherland
    0.38
    験
    0.38
    Honey
    0.37
    tube
    0.36
    Activations Density 0.001%

    No Known Activations