© 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. 67091
    Prev
    Next
    INDEX
    Explanations

    reproducibility and reliability

    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
     about
    -1.49
     árvores
    -1.38
    鶫
    -1.34
    簠
    -1.34
    quitos
    -1.33
    禟
    -1.31
     adorned
    -1.30
     wonderfully
    -1.30
     masterful
    -1.28
    
    -1.28
    POSITIVE LOGITS
     Keeping
    1.26
     despite
    1.26
    Despite
    1.25
     présidenti
    1.25
     plastico
    1.17
    8
    1.17
     Using
    1.16
    Not
    1.16
     harian
    1.16
     nearing
    1.16
    Activations Density 0.137%

    No Known Activations