© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109682
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     but
    -0.92
    acies
    -0.85
    やら
    -0.84
    itonitis
    -0.84
    いただきます
    -0.83
    缘
    -0.82
    ılık
    -0.81
     last
    -0.81
    的基础
    -0.81
     vaid
    -0.80
    POSITIVE LOGITS
    فقط
    0.97
     cambia
    0.96
     UNTIL
    0.91
    ítő
    0.90
    ۔
    0.90
     $"
    0.88
     EXAMPLES
    0.88
     aihe
    0.87
    想着
    0.86
    还想
    0.86
    Activations Density 0.011%

    No Known Activations