© 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. 118738
    Prev
    Next
    INDEX
    Explanations

    areas and licensing information

    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
     まとめ
    -0.94
     tuổi
    -0.89
    捗
    -0.88
    gruppo
    -0.84
    útbol
    -0.81
    類型
    -0.81
    ombies
    -0.79
     Kamu
    -0.79
    类型
    -0.78
     教室
    -0.77
    POSITIVE LOGITS
    Area
    1.37
     Area
    1.34
    area
    1.32
     area
    1.26
     AREA
    1.11
    Identity
    1.11
    areas
    1.09
     Areas
    1.05
    Areas
    1.04
    AREA
    0.97
    Activations Density 0.004%

    No Known Activations