© 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. 754
    Prev
    Next
    INDEX
    Explanations

    based on, focuses on

    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
    აში
    1.67
    
    1.58
    기고
    1.53
     Barcelone
    1.53
     disponibles
    1.52
    值为
    1.52
     disponible
    1.51
    Visible
    1.47
    ところに
    1.47
    ><%=
    1.47
    POSITIVE LOGITS
     solely
    2.44
     primarily
    2.25
     mainly
    2.05
     largely
    2.05
     exclusively
    2.00
     mostly
    1.95
     principally
    1.93
     predominantly
    1.92
     entirely
    1.91
     purely
    1.84
    Activations Density 1.512%

    No Known Activations