© 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. 2471
    Prev
    Next
    INDEX
    Explanations

    product reviews and purchases

    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
    gangenheit
    -1.02
     papild
    -1.00
    yoruz
    -0.98
     弹
    -0.95
     चुनें
    -0.95
    旎
    -0.94
    おかげ
    -0.88
    Garantía
    -0.86
    tą
    -0.86
     aparcamiento
    -0.86
    POSITIVE LOGITS
     I
    1.76
     bought
    1.52
     product
    1.36
     arrived
    1.35
     works
    1.27
     ordered
    1.23
     this
    1.19
     هذه
    1.19
     exactly
    1.19
     funciona
    1.12
    Activations Density 0.006%

    No Known Activations