© 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. 2678
    Prev
    Next
    INDEX
    Explanations

    maintain systems and applications

    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
    ビング
    1.16
     Horoscope
    1.15
     horario
    1.14
     Guggenheim
    1.13
    Wings
    1.13
    閨
    1.12
     governorship
    1.09
     gubernatorial
    1.09
    payer
    1.09
     geranium
    1.09
    POSITIVE LOGITS
    โต
    1.01
    Jf
    1.01
    COMP
    0.97
    軽
    0.92
    Kom
    0.90
    romb
    0.88
    CRM
    0.86
    ise
    0.86
     Leb
    0.85
    acf
    0.85
    Activations Density 0.128%

    No Known Activations