© 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. 59281
    Prev
    Next
    INDEX
    Explanations

    programmers prefer dark mode

    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
    Está
    0.44
     sedang
    0.41
     selectively
    0.40
     selective
    0.39
    Selective
    0.38
    indsight
    0.37
     *$
    0.36
     đang
    0.35
     cukup
    0.35
    Northern
    0.35
    POSITIVE LOGITS
     prefer
    1.13
    prefer
    1.00
     Prefer
    0.99
     prefers
    0.99
     предпочита
    0.94
    Prefer
    0.93
     preferring
    0.91
    不喜欢
    0.91
     싫
    0.85
     preference
    0.83
    Activations Density 0.001%

    No Known Activations