© 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-262K
    7. 21169
    Prev
    Next
    INDEX
    Explanations

    neural network and patient similarity

    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
    物资
    0.44
    වැ
    0.44
     estrutura
    0.43
    澧
    0.43
    शुदा
    0.42
    Weekly
    0.40
    perluan
    0.40
    𝐖
    0.39
     نئی
    0.39
    प्र
    0.39
    POSITIVE LOGITS
     或者
    0.50
     retrieval
    0.48
     authentication
    0.46
     leverages
    0.46
     refers
    0.44
     indentation
    0.44
     disamb
    0.43
     syndrome
    0.43
     leveraging
    0.43
     entails
    0.43
    Activations Density 0.052%

    No Known Activations