© 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. 39976
    Prev
    Next
    INDEX
    Explanations

    sports vocabulary

    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
    If
    -1.55
    >
    -1.51
    During
    -1.48
    %;
    -1.47
     που
    -1.45
    Because
    -1.43
    ḿ
    -1.42
    ’
    -1.41
    </i>
    -1.38
     haka
    -1.37
    POSITIVE LOGITS
     İyi
    1.48
     sukces
    1.48
     asamblea
    1.48
     obuv
    1.45
     sección
    1.45
    inatal
    1.45
    richtig
    1.39
     zákaz
    1.38
    ändigen
    1.37
    blusa
    1.34
    Activations Density 0.008%

    No Known Activations