© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49376
    Prev
    Next
    INDEX
    Explanations

    numbers after dash or equals

    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
    全て
    -1.53
    ⩽
    -1.26
    すべて
    -1.15
     küche
    -1.11
    ubility
    -1.08
     inapropiados
    -1.07
     сериал
    -1.05
    ⩾
    -1.05
     тысяч
    -1.05
    其他
    -1.05
    POSITIVE LOGITS
     объяс
    1.04
    変わらず
    1.02
     ratific
    0.99
    貼り
    0.98
    ㌘
    0.97
     duce
    0.96
     Comunic
    0.94
     Profesional
    0.94
     procla
    0.94
    話が
    0.93
    Activations Density 0.201%

    No Known Activations