© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110430
    Prev
    Next
    INDEX
    Explanations

    it is/was

    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
     limitada
    -0.94
    になりました
    -0.94
    関係
    -0.85
     berechnet
    -0.81
     limitado
    -0.79
     controlada
    -0.79
    腆
    -0.79
     wüns
    -0.78
     FontWeight
    -0.78
     resembles
    -0.77
    POSITIVE LOGITS
     is
    2.06
     Именно
    1.48
    是
    1.46
     are
    1.42
     là
    1.38
     именно
    1.36
     adalah
    1.21
     είναι
    1.20
    のは
    1.16
    是在
    1.05
    Activations Density 0.020%

    No Known Activations