© 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. 64380
    Prev
    Next
    INDEX
    Explanations

    Spanish words, movement, or trick questions

    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
     spinner
    0.41
    न्दु
    0.40
     billy
    0.38
    Scaler
    0.37
    olni
    0.37
    Spinner
    0.37
    Ꮵ
    0.36
    পুত্র
    0.36
     қол
    0.36
    billy
    0.36
    POSITIVE LOGITS
     corrid
    0.43
     *=
    0.39
     научной
    0.39
     حک
    0.38
    PERS
    0.38
    Apellido
    0.38
     corrida
    0.37
    cijas
    0.37
    혼
    0.37
    믹
    0.37
    Activations Density 1.185%

    No Known Activations