© 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. 40-GEMMASCOPE-2-RES-262K
    7. 132253
    Prev
    Next
    INDEX
    Explanations

    complex clauses and algorithms

    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
     spending
    0.41
    ె
    0.40
    鬚
    0.39
    ិត
    0.38
     побы
    0.38
     extremists
    0.38
    ذن
    0.37
     चेतन
    0.37
     protest
    0.37
     train
    0.37
    POSITIVE LOGITS
    ipped
    0.45
     QuantityOnHand
    0.42
    ech
    0.39
    CLA
    0.38
    偈
    0.38
    echo
    0.38
    𒉡
    0.38
    March
    0.37
    flipped
    0.37
    wParam
    0.37
    Activations Density 0.000%

    No Known Activations