© 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. 130607
    Prev
    Next
    INDEX
    Explanations

    code blocks and formatting

    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
    ‛
    0.40
    啓
    0.39
    ‹
    0.39
     जोर
    0.38
    喈
    0.37
     Floors
    0.36
     استعداد
    0.36
    میر
    0.36
    <ul>
    0.35
     عزی
    0.35
    POSITIVE LOGITS
    dec
    0.41
     underscores
    0.40
    intend
    0.39
     typos
    0.39
     kud
    0.38
     acup
    0.38
    vart
    0.38
    ldots
    0.38
     ruang
    0.37
     ತಾ
    0.37
    Activations Density 0.000%

    No Known Activations