© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47225
    Prev
    Next
    INDEX
    Explanations

    investigate your data

    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_65k_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
    자
    0.45
    의
    0.45
    商
    0.44
    のない
    0.44
    ो
    0.43
    گ
    0.43
    송
    0.43
    시
    0.42
    ت
    0.42
    の
    0.42
    POSITIVE LOGITS
     condivid
    0.42
    ractor
    0.41
     می‌تواند
    0.41
     соба
    0.41
    🏈
    0.41
     እንዴት
    0.40
    ⚤
    0.40
     ребен
    0.40
     consultez
    0.40
     হত্যা
    0.39
    Activations Density 0.001%

    No Known Activations