© 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. 64971
    Prev
    Next
    INDEX
    Explanations

    code SDK imports

    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
    i
    0.31
    j
    0.29
    cY
    0.28
    dh
    0.27
    erto
    0.26
    homme
    0.26
    িলে
    0.26
    GUI
    0.26
    "--
    0.26
    toString
    0.26
    POSITIVE LOGITS
     mischiev
    0.33
     causado
    0.31
    MeshData
    0.30
    اسية
    0.30
    ាត់
    0.30
     Перейти
    0.30
    ន្ល
    0.29
     GetData
    0.29
     unwittingly
    0.29
     academies
    0.29
    Activations Density 0.001%

    No Known Activations