© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27521
    Prev
    Next
    INDEX
    Explanations

    count of items followed by separators

    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/layer_40_width_262k_l0_medium
    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
     distributes
    0.42
    ௫
    0.41
    hô
    0.39
    ဍ
    0.39
     plr
    0.38
     catholic
    0.38
     whereof
    0.38
    काउंट
    0.37
    笑道
    0.37
    閲
    0.37
    POSITIVE LOGITS
     уже
    0.40
    already
    0.38
     sebenarnya
    0.37
    Bub
    0.35
    循环
    0.35
     already
    0.34
    เพื่อให้
    0.34
    其实
    0.34
    Already
    0.34
     Mandela
    0.34
    Activations Density 0.000%

    No Known Activations