© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26273
    Prev
    Next
    INDEX
    Explanations

    sentence ending emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    😐
    -2.47
    👎
    -2.34
    😒
    -2.34
    😠
    -2.31
    💀
    -2.25
    👍👍
    -2.25
    😔
    -2.25
    😥
    -2.25
    OOOOO
    -2.20
    😑
    -2.20
    POSITIVE LOGITS
     It
    3.27
    This
    2.70
    1
    2.56
    There
    2.44
    ↵
    2.30
     This
    2.30
     they
    2.28
     The
    2.28
    Since
    2.28
     There
    2.23
    Activations Density 0.049%

    No Known Activations