© 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. 40-GEMMASCOPE-2-RES-262K
    7. 166728
    Prev
    Next
    INDEX
    Explanations

    develop, create, generate

    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
    Kin
    0.39
    ுற
    0.38
    霓
    0.37
     superintend
    0.36
    onents
    0.36
    抒
    0.36
     निर्वा
    0.36
     rnorm
    0.35
     Superintend
    0.35
    ირ
    0.35
    POSITIVE LOGITS
     allergens
    0.41
     gaps
    0.39
     reacts
    0.38
     sediment
    0.38
     одного
    0.38
     differences
    0.36
    ใช
    0.36
     শেষে
    0.36
     spots
    0.35
    %$
    0.35
    Activations Density 0.001%

    No Known Activations