© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 538
    Prev
    Next
    INDEX
    Explanations

    efficient and durable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    venv
    1.35
     konto
    1.32
     convoc
    1.32
     prelude
    1.31
     Koordin
    1.30
     unpaid
    1.24
     関係
    1.22
     "~/
    1.21
     Frege
    1.19
    episode
    1.18
    POSITIVE LOGITS
     durability
    2.58
     durable
    2.39
    耐久
    2.20
     Durable
    2.05
     resistant
    2.03
     withstand
    1.98
     robustness
    1.95
     toughness
    1.93
     unbreakable
    1.86
     breathable
    1.85
    Activations Density 7.116%

    No Known Activations