© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118609
    Prev
    Next
    INDEX
    Explanations

    system performance and timing

    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
    цене
    -0.79
    藪
    -0.77
     ネックレス
    -0.76
    itsch
    -0.75
     بیت
    -0.75
     TELEPHONE
    -0.74
    桅
    -0.72
     öld
    -0.72
    เงิน
    -0.70
    nadier
    -0.70
    POSITIVE LOGITS
     latency
    1.09
     response
    0.97
     Latency
    0.92
    Latency
    0.92
    Concurrency
    0.83
     Responding
    0.82
     responding
    0.82
    laten
    0.81
    latency
    0.81
     throughput
    0.79
    Activations Density 0.034%

    No Known Activations