© 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. 44404
    Prev
    Next
    INDEX
    Explanations

    curling championships and physics models

    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
     クッション
    -1.27
    etsen
    -1.20
     Lê
    -1.16
     péché
    -1.15
     jouet
    -1.13
    짭
    -1.13
     $\}$
    -1.11
     herramienta
    -1.09
    hamed
    -1.09
    ği
    -1.09
    POSITIVE LOGITS
     more
    1.45
     both
    1.14
    </i>
    1.13
     like
    1.11
     A
    1.08
    ll
    1.08
    </b>
    1.07
     percent
    1.07
     using
    1.06
     many
    1.05
    Activations Density 0.041%

    No Known Activations