Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7741
    Prev
    Next
    INDEX
    Explanations

    code comments or definitions

    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
     Estos
    -0.94
     Söz
    -0.91
     Estas
    -0.90
     GF
    -0.84
    odyear
    -0.78
     sleepless
    -0.77
    ッポン
    -0.77
    фильм
    -0.76
    Kobe
    -0.76
    モーション
    -0.75
    POSITIVE LOGITS
     distorted
    0.89
     vectoriales
    0.85
     luxurious
    0.85
    kově
    0.84
    렉
    0.83
     olie
    0.82
     brune
    0.82
     birds
    0.81
    strained
    0.80
     klik
    0.80
    Activations Density 0.002%

    No Known Activations