© 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. 10-GEMMASCOPE-RES-131K
    7. 8139
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action completion or initiation

    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_10/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
    垆
    -1.34
     Welche
    -1.27
     Verhalten
    -1.27
     verschillende
    -1.27
     lettura
    -1.21
     saiba
    -1.14
    蛏
    -1.13
     further
    -1.13
     controllare
    -1.13
     professores
    -1.12
    POSITIVE LOGITS
     by
    1.62
     чехол
    1.34
     on
    1.26
    塬
    1.20
     бампер
    1.17
    也非常
    1.14
    上記の
    1.14
    孪
    1.14
    неш
    1.13
     brightest
    1.13
    Activations Density 0.107%

    No Known Activations