© 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. 110488
    Prev
    Next
    INDEX
    Explanations

    journalism, echocardiography, model, token

    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
     laku
    -0.93
     bakar
    -0.89
    
    -0.87
     kemasan
    -0.86
     pasien
    -0.84
     mawar
    -0.84
    livejournal
    -0.82
     kolam
    -0.81
     pisang
    -0.81
     kafe
    -0.78
    POSITIVE LOGITS
    зию
    0.88
     tour
    0.87
    dinga
    0.86
     synthèse
    0.86
    ๊ก
    0.85
    czny
    0.82
     pulleys
    0.82
     tours
    0.81
    swal
    0.80
    的问道
    0.80
    Activations Density 0.000%

    No Known Activations