© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9004
    Prev
    Next
    INDEX
    Explanations

    expressive punctuation and actions

    np_acts-logits-general · gemini-2.5-flash-lite

    happy ending punctuation

    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_40_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
     ..."
    0.48
     ...)
    0.47
     nbsp
    0.39
    <td>
    0.38
     ""`
    0.38
     AKA
    0.36
    ...)
    0.34
    ...”
    0.34
     appartiennent
    0.34
    “
    0.33
    POSITIVE LOGITS
    !
    0.93
    ؛
    0.91
     :)
    0.89
    !!!
    0.85
    !!
    0.84
     🙂
    0.84
    ！
    0.82
    !!!!
    0.79
    ။
    0.79
     😉
    0.79
    Activations Density 2.759%

    No Known Activations