© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129732
    Prev
    Next
    INDEX
    Explanations

    object level, icon options

    np_acts-logits-general · gemini-2.5-flash-lite

    rules for passing and case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    망
    0.48
    人群
    0.47
     liquides
    0.44
     جي
    0.44
    𝐑
    0.43
     সপ্তাহ
    0.43
     അവര്‍
    0.41
    cemment
    0.41
    꺾
    0.41
    нде
    0.41
    POSITIVE LOGITS
    s
    0.67
     pictogram
    0.58
    ی
    0.52
     an
    0.52
     level
    0.50
    Kotlin
    0.50
     physics
    0.49
     CS
    0.49
     descriptive
    0.49
    UN
    0.48
    Activations Density 0.001%

    No Known Activations