© 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. 143398
    Prev
    Next
    INDEX
    Explanations

    commit title or shared passions

    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
     اسپ
    0.49
     Quels
    0.47
    ²)
    0.44
     STD
    0.44
     creatine
    0.44
    オリ
    0.44
     Chou
    0.43
     Guys
    0.43
     accentuated
    0.42
     painkillers
    0.42
    POSITIVE LOGITS
     ali
    0.49
    جست
    0.49
     ciento
    0.47
    vis
    0.46
    闿
    0.46
    director
    0.44
    هِ
    0.44
    وية
    0.43
    wise
    0.43
    dokument
    0.43
    Activations Density 0.001%

    No Known Activations