© 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. 118931
    Prev
    Next
    INDEX
    Explanations

    bullet points and lists

    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
     наря
    -0.82
    取締
    -0.81
    amos
    -0.81
     поступ
    -0.78
     ***
    -0.76
    告诉你
    -0.75
     **
    -0.74
    諜
    -0.74
     GL
    -0.70
     dinner
    -0.69
    POSITIVE LOGITS
    *
    0.90
     ・
    0.85
     ⋅
    0.84
     shite
    0.83
    itemize
    0.83
     
    0.82
    
    0.82
    ﾕ
    0.81
     ●
    0.80
    ↨
    0.79
    Activations Density 0.119%

    No Known Activations