© 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. 10-GEMMASCOPE-RES-131K
    7. 66819
    Prev
    Next
    INDEX
    Explanations

    flight MHprimrose oilreflexologydefrost heaterAir India

    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_10/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
     verstor
    -2.11
    д
    -1.63
     erwähnten
    -1.57
     ใหญ่
    -1.53
     glaubte
    -1.51
     wußte
    -1.50
     zugel
    -1.45
     wusste
    -1.44
    巿
    -1.43
     deutscher
    -1.42
    POSITIVE LOGITS
    id
    1.90
     kereta
    1.73
     }
    1.73
     рынке
    1.72
     tornillos
    1.68
    ’
    1.63
    逦
    1.61
     exige
    1.60
    由于
    1.60
    au
    1.60
    Activations Density 0.030%

    No Known Activations