© 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. 4053
    Prev
    Next
    INDEX
    Explanations

    *

    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
    '!
    2.86
    ,
    2.71
    ’!
    2.70
    -
    2.59
    ,\\
    2.56
    ,\"
    2.50
    ',
    2.48
    ,}
    2.47
    ’:
    2.45
    '?
    2.43
    POSITIVE LOGITS
     The
    2.25
     There
    2.13
     If
    2.03
    The
    2.02
     When
    2.02
     Assuming
    2.02
     Finally
    1.91
     Although
    1.89
    When
    1.89
     Because
    1.83
    Activations Density 0.198%

    No Known Activations