© 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. 2392
    Prev
    Next
    INDEX
    Explanations

    special characters or punctuation

    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
    ophyte
    0.46
    (",",
    0.44
    逻辑
    0.42
    ocou
    0.41
    楨
    0.41
    ALSE
    0.41
    Acetic
    0.41
    Bep
    0.40
    oran
    0.40
     dimensionality
    0.40
    POSITIVE LOGITS
    🕊
    0.42
     &,
    0.39
     Slovak
    0.39
     TikTok
    0.38
     gir
    0.38
    𝚃
    0.38
     महासभा
    0.38
     spend
    0.38
    trainer
    0.38
     Tiktok
    0.37
    Activations Density 0.000%

    No Known Activations