© 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. 6641
    Prev
    Next
    INDEX
    Explanations

    LaTeX environments and commands

    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
    ុស
    0.54
    carbonyl
    0.49
     geometrical
    0.47
    ϩ
    0.47
     qualités
    0.46
    َص
    0.46
     vessie
    0.46
    opherol
    0.46
    ضور
    0.45
    َم
    0.45
    POSITIVE LOGITS
    tikzpicture
    0.58
     Mult
    0.57
     Flush
    0.55
    enumerate
    0.55
     Document
    0.54
    thebibliography
    0.53
     Sco
    0.52
     center
    0.51
    align
    0.51
     Sid
    0.51
    Activations Density 0.001%

    No Known Activations