© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89724
    Prev
    Next
    INDEX
    Explanations

    cutting and polishing 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
     OLED
    -0.85
     hoá
    -0.79
    itename
    -0.70
     Ugo
    -0.69
    IHC
    -0.69
    danh
    -0.68
     CFL
    -0.67
    誇
    -0.67
     ECR
    -0.67
    Deposits
    -0.66
    POSITIVE LOGITS
     polishing
    1.64
     polished
    1.58
     polish
    1.55
    polished
    1.27
     Polished
    1.14
     grinding
    1.11
     cut
    1.05
    polish
    1.05
    Pol
    1.00
    cut
    0.98
    Activations Density 0.021%

    No Known Activations