© 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. 119081
    Prev
    Next
    INDEX
    Explanations

    mode cluster

    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
     Samos
    -0.75
     barre
    -0.74
     Sous
    -0.72
     collet
    -0.71
     Auschwitz
    -0.70
    cdnjs
    -0.70
    ジム
    -0.69
     lemmas
    -0.69
     correc
    -0.68
     mida
    -0.68
    POSITIVE LOGITS
     resource
    0.97
     application
    0.97
     Application
    0.96
    Application
    0.93
    КС
    0.88
     forsø
    0.85
     zab
    0.85
     attempt
    0.85
     recurso
    0.82
    AM
    0.82
    Activations Density 0.008%

    No Known Activations