© 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. 33665
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
    :
    -1.18
     quí
    -1.16
     Estas
    -1.09
    ator
    -1.06
     eer
    -1.04
     Arkivert
    -1.04
     Each
    -1.02
    gató
    -1.02
     шт
    -1.00
     américa
    -1.00
    POSITIVE LOGITS
     można
    1.29
    رسد
    1.24
     couldn
    1.19
     didn
    1.18
     how
    1.11
     такого
    1.10
     what
    1.09
     collectively
    1.05
    什么样的
    1.05
     hardly
    1.04
    Activations Density 0.018%

    No Known Activations