© 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. 3867
    Prev
    Next
    INDEX
    Explanations

    eliminate the incorrect

    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
    تيجة
    1.21
    <u>
    1.19
    oven
    1.13
    Downward
    1.05
     teclas
    0.99
    UD
    0.99
    TV
    0.98
    Television
    0.97
     trono
    0.97
    rafa
    0.95
    POSITIVE LOGITS
    фы
    1.81
     '%'
    1.75
     wier
    1.72
     varied
    1.70
     типо
    1.70
     feste
    1.66
     kuchh
    1.66
     varier
    1.66
     metody
    1.65
     verschillende
    1.65
    Activations Density 0.003%

    No Known Activations