© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82275
    Prev
    Next
    INDEX
    Explanations

    inside, therein, on it

    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
     ici
    -0.87
     aqui
    -0.84
     acá
    -0.83
     lors
    -0.79
    Lycka
    -0.77
     هناك
    -0.77
     اینجا
    -0.77
     כאן
    -0.76
     Up
    -0.74
     جایی
    -0.73
    POSITIVE LOGITS
     darin
    2.02
     therein
    1.97
     dedans
    1.95
     فيه
    1.62
     dessus
    1.58
     thereon
    1.48
    そこに
    1.34
     इसमें
    1.27
     it
    1.26
     inside
    1.26
    Activations Density 0.118%

    No Known Activations