© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 247764
    Prev
    Next
    INDEX
    Explanations

    world or way home

    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
    Not in Any Lists

    No Comments

    Negative Logits
     чи
    0.46
    Amendment
    0.45
    ToWrite
    0.44
    Funds
    0.44
    霏
    0.43
    рил
    0.42
    ፃ
    0.42
    Disponible
    0.42
     trifle
    0.41
    ລ
    0.41
    POSITIVE LOGITS
     Dtsch
    0.52
    nabla
    0.46
    podob
    0.46
     Kompet
    0.45
     Seorang
    0.44
     먼저
    0.44
     către
    0.44
     মেয়র
    0.43
    醫師
    0.43
     ဦး
    0.42
    Activations Density 0.001%

    No Known Activations