© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 33
    Prev
    Next
    INDEX
    Explanations

    commas followed by conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
    4
    0.41
     are
    0.40
     for
    0.39
    5
    0.36
     ने
    0.34
     ४
    0.33
    <0x0D>
    0.31
    FOUR
    0.31
    five
    0.30
     t
    0.29
    POSITIVE LOGITS
    t
    0.44
    l
    0.37
    d
    0.35
    g
    0.34
    b
    0.33
    n
    0.32
    as
    0.32
    c
    0.31
    h
    0.30
    antera
    0.29
    Activations Density 2.995%

    No Known Activations