© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22949
    Prev
    Next
    INDEX
    Explanations

    Ukraine, account, expression

    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
     ì
    0.46
    很多的
    0.46
    Ğ
    0.45
     একটি
    0.44
    ใน
    0.41
    â
    0.41
    Ĺ
    0.41
     ஒரு
    0.40
    ภ
    0.40
    ຳ
    0.40
    POSITIVE LOGITS
     plupart
    0.46
     czasie
    0.43
    之际
    0.41
    理由は
    0.40
     wichtigsten
    0.39
     vostri
    0.38
    same
    0.38
    basis
    0.38
     julio
    0.38
     plaît
    0.38
    Activations Density 0.040%

    No Known Activations