© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102134
    Prev
    Next
    INDEX
    Explanations

    minerals and ore processing

    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
    区别
    -1.51
    ();
    
    -1.47
     男の子
    -1.41
     یا
    -1.41
    卣
    -1.40
     benutzen
    -1.37
    做过
    -1.33
    ]},
    -1.30
    ças
    -1.28
    dération
    -1.28
    POSITIVE LOGITS
     folgende
    1.40
     หลัง
    1.31
     another
    1.31
    いただきたい
    1.26
     minerals
    1.23
    emiah
    1.20
     Когда
    1.20
     otro
    1.17
     resources
    1.16
    应该
    1.15
    Activations Density 0.065%

    No Known Activations