© 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. 118870
    Prev
    Next
    INDEX
    Explanations

    brands and ingredients

    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
    旅館
    -0.96
    現象
    -0.82
     autentic
    -0.80
     recic
    -0.79
    母親
    -0.79
     fertilization
    -0.78
    ใช้งาน
    -0.78
     последствия
    -0.77
    コピー
    -0.74
     mancha
    -0.74
    POSITIVE LOGITS
     ļoti
    0.88
    処
    0.86
    ographed
    0.85
    Poland
    0.85
     beverly
    0.82
    MD
    0.81
    נשים
    0.81
    為に
    0.81
    FFECT
    0.81
    tinya
    0.81
    Activations Density 0.056%

    No Known Activations