© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 202800
    Prev
    Next
    INDEX
    Explanations

    causes or describes relationships

    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
    샀
    0.47
     부동산
    0.47
     जनगणना
    0.47
     డబ్బు
    0.47
    蘄
    0.46
    買
    0.46
     منصوبہ
    0.46
     खरीदी
    0.46
    <unused354>
    0.45
     основные
    0.44
    POSITIVE LOGITS
     ton
    0.43
     confort
    0.42
     will
    0.40
     sem
    0.39
     jung
    0.39
     cryst
    0.38
     Dragon
    0.38
     guest
    0.38
     krist
    0.38
     horseshoe
    0.38
    Activations Density 0.004%

    No Known Activations