© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 10109
    Prev
    Next
    INDEX
    Explanations

    words followed by exclamation marks

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

    emphatic punctuation after requests

    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
     whatnot
    0.59
     อืม
    0.46
    ্ম
    0.46
    <unused2162>
    0.45
     برضو
    0.44
     ebenfalls
    0.43
     idk
    0.42
     거고
    0.42
     मकसद
    0.42
     cunt
    0.41
    POSITIVE LOGITS
    !
    3.11
    !
    2.77
    !)
    2.64
    !\
    2.56
    !).
    2.53
    !</
    2.53
    !]
    2.53
    !),
    2.52
    !!
    2.50
    !"
    2.50
    Activations Density 1.662%

    No Known Activations