© 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. 23507
    Prev
    Next
    INDEX
    Explanations

    train test split

    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
    供給
    0.40
    Rank
    0.38
    兢
    0.38
    Projection
    0.38
    ൨
    0.38
    feeding
    0.37
     feeding
    0.36
    рку
    0.36
    apd
    0.36
    悼
    0.35
    POSITIVE LOGITS
     split
    1.23
    split
    1.09
     Split
    1.08
     splitting
    1.06
    Split
    1.03
     splits
    0.99
    splitting
    0.94
     разде
    0.90
     Splits
    0.88
    splits
    0.86
    Activations Density 0.017%

    No Known Activations