© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5078
    Prev
    Next
    INDEX
    Explanations

    paid advertising

    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_16k_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
     rhinophores
    0.48
    纤维
    0.47
    萜
    0.45
     بھی
    0.45
     사람들
    0.45
    ಗಾರ
    0.44
    زاب
    0.43
    拏
    0.43
     cytoplasm
    0.42
     sillons
    0.42
    POSITIVE LOGITS
    co
    0.50
    that
    0.48
    cal
    0.46
    un
    0.46
    aiman
    0.45
    do
    0.45
    bling
    0.45
    especially
    0.45
    Y
    0.44
    dummy
    0.44
    Activations Density 0.174%

    No Known Activations