© 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. 3939
    Prev
    Next
    INDEX
    Explanations

    better I

    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
    plit
    1.47
    فير
    1.24
     contraire
    1.21
    versus
    1.20
     contrario
    1.19
    <blockquote>
    1.15
    icoli
    1.12
    itektur
    1.10
     fringilla
    1.10
    𝙉
    1.10
    POSITIVE LOGITS
     aún
    2.34
     still
    2.27
     todavía
    2.25
    still
    2.16
     STILL
    2.13
     nutric
    2.00
     yet
    2.00
     disconnected
    1.98
    rils
    1.93
     reliably
    1.92
    Activations Density 0.092%

    No Known Activations