© 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. 165761
    Prev
    Next
    INDEX
    Explanations

    numbers, codes, and academic terms

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

    QA engineers work and tools

    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
    زالة
    0.50
    拯救
    0.49
    лово
    0.48
    ⟣
    0.45
    نوان
    0.45
     democratization
    0.45
    べく
    0.45
    ستوى
    0.45
    सर्ग
    0.44
    henko
    0.44
    POSITIVE LOGITS
     мили
    0.48
     स्कूल
    0.45
     үчүн
    0.45
     fréquente
    0.44
    E
    0.43
     우선
    0.43
     Кей
    0.42
     institut
    0.42
    Error
    0.42
    Sketch
    0.41
    Activations Density 0.006%

    No Known Activations