© 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. 131541
    Prev
    Next
    INDEX
    Explanations

    Succession

    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
     Пор
    0.40
     skew
    0.38
     मदर
    0.37
    訲
    0.37
     dri
    0.36
     derive
    0.35
     bande
    0.35
     port
    0.35
    aluronic
    0.35
    𒀝
    0.35
    POSITIVE LOGITS
    IEF
    0.41
    لاث
    0.40
    inputs
    0.39
    <unused47>
    0.39
     Publicity
    0.38
     حذف
    0.38
    Ꮏ
    0.38
     অনুস
    0.37
     SEP
    0.37
    ক্ষিতে
    0.37
    Activations Density 0.047%

    No Known Activations