© 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. 34-GEMMASCOPE-RES-131K
    7. 58313
    Prev
    Next
    INDEX
    Explanations

    furnace, coke, slag, and molten materials

    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_34/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
    Spacer
    -0.85
    muş
    -0.80
     signifikan
    -0.76
    apura
    -0.75
    DEPORTES
    -0.74
     senescence
    -0.74
    utze
    -0.73
    ksjoner
    -0.73
    lum
    -0.72
    thresh
    -0.72
    POSITIVE LOGITS
     Slag
    1.08
     coke
    1.06
     blast
    1.05
     slag
    1.05
     blowing
    1.05
     Coke
    0.97
     шла
    0.97
     furnace
    0.96
     charge
    0.96
     matte
    0.93
    Activations Density 0.045%

    No Known Activations