© 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. 21538
    Prev
    Next
    INDEX
    Explanations

    need or want something

    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
     attirer
    -1.21
     accueillir
    -1.20
    难过
    -1.16
    titian
    -1.13
     بسبب
    -1.11
    颤抖
    -1.10
     reveló
    -1.09
    下意识
    -1.09
     Corsica
    -1.06
     seraient
    -1.05
    POSITIVE LOGITS
     que
    1.44
    )):
    1.36
    bodyParser
    1.34
    </tfoot>
    1.27
     ebenfalls
    1.24
    initializeApp
    1.23
    ^*)
    1.23
     汁
    1.23
     árbitro
    1.22
     who
    1.21
    Activations Density 0.041%

    No Known Activations