© 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. 2155
    Prev
    Next
    INDEX
    Explanations

    coupon code for offer

    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
    +");
    -0.85
     男の子
    -0.75
     Osorio
    -0.74
    Booked
    -0.73
     andern
    -0.73
    說道
    -0.73
    ︴
    -0.72
    neighbor
    -0.71
    Œ
    -0.71
     maisha
    -0.71
    POSITIVE LOGITS
     code
    3.28
     use
    2.72
     código
    2.36
    code
    2.25
     Code
    2.11
     coupon
    2.11
    CODE
    2.05
     codes
    2.03
     Use
    2.02
    Code
    1.99
    Activations Density 0.023%

    No Known Activations