© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1878
    Prev
    Next
    INDEX
    Explanations

    closing quotes and parentheses

    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
     They
    1.09
     Their
    1.06
    They
    1.04
    
    1.03
    ßt
    1.02
    their
    1.02
    »
    1.02
     they
    1.02
     »
    1.01
    ū
    1.00
    POSITIVE LOGITS
    ））
    4.95
    "))
    4.93
    '))
    4.70
     "))
    4.44
     '))
    4.38
    ."))
    4.31
    )).
    4.26
    .)).
    4.16
    ()))
    4.13
    :"))
    4.13
    Activations Density 0.108%

    No Known Activations