© 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. 77655
    Prev
    Next
    INDEX
    Explanations

    Python, French, Portuguese, Japanese, web services

    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
     has
    -1.23
     provided
    -1.23
     blistering
    -1.20
     spurred
    -1.18
     came
    -1.15
     helped
    -1.14
     sparked
    -1.13
     Using
    -1.10
     may
    -1.09
     appears
    -1.09
    POSITIVE LOGITS
     favoriser
    1.46
     nettoyer
    1.45
     diriger
    1.38
    がありますが
    1.34
    鼍
    1.33
     thoſe
    1.31
     imprimer
    1.30
    
    1.27
     relâche
    1.27
     autonomie
    1.27
    Activations Density 0.027%

    No Known Activations