© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3919
    Prev
    Next
    INDEX
    Explanations

    Shinjuku Shibuya

    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
     poids
    1.74
     fasci
    1.67
     punti
    1.61
    部位
    1.56
     apariencia
    1.53
    붉
    1.53
     garnet
    1.52
     bizony
    1.51
     tact
    1.49
     assolutamente
    1.49
    POSITIVE LOGITS
    ondon
    1.18
     》
    1.18
    》
    1.12
    uries
    1.07
    북
    1.04
    sonian
    1.04
     Salut
    1.01
    visor
    1.00
    }<\
    0.99
    otron
    0.97
    Activations Density 0.024%

    No Known Activations