© 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. 84213
    Prev
    Next
    INDEX
    Explanations

    steel industry

    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
     zabezpiec
    -1.32
     uszkod
    -1.30
    ppchen
    -1.29
    پا
    -1.25
     ciała
    -1.23
     pomiesz
    -1.23
    그러나
    -1.22
     хочет
    -1.22
     necesitas
    -1.19
     sustancias
    -1.16
    POSITIVE LOGITS
     accordingly
    1.27
     чет
    1.25
    </h4>
    1.16
     kelapa
    1.15
    ти
    1.13
     lebaran
    1.12
    Gotham
    1.11
     Which
    1.09
     komplette
    1.09
     assistência
    1.07
    Activations Density 0.053%

    No Known Activations