© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56628
    Prev
    Next
    INDEX
    Explanations

    origin or source

    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
    Negative Logits
     です
    0.44
    ្នុង
    0.42
     thereunder
    0.40
     önemlidir
    0.38
     रोकने
    0.38
    निर्भर
    0.38
     पड़ता
    0.38
     ढक
    0.38
     dana
    0.37
    銷
    0.37
    POSITIVE LOGITS
    来自
    1.28
    來自
    1.23
    来自于
    1.20
    จาก
    1.17
     provenant
    1.17
     from
    1.14
     från
    1.13
    from
    1.10
    มาจาก
    1.08
     từ
    1.05
    Activations Density 0.361%

    No Known Activations