© 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. 119010
    Prev
    Next
    INDEX
    Explanations

    credit effort, Q:, A hybrid

    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
     území
    -1.04
     demographics
    -0.97
     يمكنك
    -0.94
     Viagra
    -0.94
     Луч
    -0.94
     komplett
    -0.93
     baseline
    -0.93
     jaunes
    -0.90
     milliards
    -0.90
    ūra
    -0.90
    POSITIVE LOGITS
    hdashline
    1.09
    adakan
    1.00
     helps
    0.94
     firms
    0.92
    Помо
    0.91
    Купить
    0.91
     poderá
    0.90
     cristo
    0.87
     crores
    0.86
     tebal
    0.85
    Activations Density 0.012%

    No Known Activations