© 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. 10-GEMMASCOPE-RES-131K
    7. 515
    Prev
    Next
    INDEX
    Explanations

    ja

    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_10/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
    铼
    -2.80
    
    -2.73
    ⬯
    -2.58
    我没
    -2.58
    there
    -2.52
    vaný
    -2.50
     hundred
    -2.41
    祧
    -2.41
    .
    -2.38
    鲧
    -2.38
    POSITIVE LOGITS
    ja
    2.58
     pitfalls
    2.36
    𖣔
    2.31
     perils
    2.30
    y
    2.22
     brainstorm
    2.22
     serait
    2.20
     thwart
    2.16
    ⻬
    2.14
     подготовки
    2.13
    Activations Density 0.005%

    No Known Activations