© 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. 138173
    Prev
    Next
    INDEX
    Explanations

    certain phrase continuations

    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
    成
    0.49
    تد
    0.48
     afforded
    0.47
    fread
    0.47
     shelved
    0.47
    ilerini
    0.46
    nemouth
    0.46
    trong
    0.45
    㢳
    0.45
    टा
    0.44
    POSITIVE LOGITS
     ホワイト
    0.45
    ook
    0.44
    SEM
    0.44
    System
    0.44
     UnitTest
    0.42
     ي
    0.42
    Century
    0.42
    Reference
    0.41
    Export
    0.41
    Computing
    0.41
    Activations Density 0.001%

    No Known Activations