© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45031
    Prev
    Next
    INDEX
    Explanations

    local focus

    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_31_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
     calci
    0.47
    equalTo
    0.46
     FIVE
    0.45
    數字
    0.45
    शिव
    0.44
     HOPE
    0.44
    ज्ञात
    0.44
    <0x0D>
    0.44
     ৰ
    0.43
     نیوز
    0.42
    POSITIVE LOGITS
     a
    0.47
    io
    0.46
    H
    0.45
    ali
    0.45
     or
    0.45
    les
    0.44
     insulated
    0.44
    lieder
    0.43
    ał
    0.42
    uv
    0.42
    Activations Density 0.001%

    No Known Activations