© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7571
    Prev
    Next
    INDEX
    Explanations

    numbers with units or common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    其余
    1.30
     and
    1.18
    และ
    1.18
     и
    1.15
    ضاف
    1.14
     almost
    1.12
     كافة
    1.11
    および
    1.11
     جميع
    1.11
    дея
    1.09
    POSITIVE LOGITS
     naro
    1.20
    izan
    1.17
     ඔබේ
    1.17
     גי
    1.16
     Bä
    1.13
     mavi
    1.13
     ev
    1.12
     eviction
    1.11
    ⏎
    1.11
     Bož
    1.10
    Activations Density 0.108%

    No Known Activations