© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92497
    Prev
    Next
    INDEX
    Explanations

    steel and related words

    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
     scramble
    -1.02
     glassware
    -0.92
     Freem
    -0.87
     desenli
    -0.86
     борьбе
    -0.82
     stumbled
    -0.81
     leaky
    -0.81
     víc
    -0.81
     scooped
    -0.81
     disagreement
    -0.81
    POSITIVE LOGITS
    Steel
    1.13
     steel
    1.08
    steel
    1.07
     Steel
    1.07
     preocupes
    0.98
    ),
    0.96
     Magno
    0.96
     koje
    0.93
     stål
    0.91
     inoxidable
    0.90
    Activations Density 0.007%

    No Known Activations