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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83681
    Prev
    Next
    INDEX
    Explanations

    year statistics

    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
     Qo
    -0.79
     tabu
    -0.77
    ഢ
    -0.76
    𝔼
    -0.75
     piłkarz
    -0.74
    phide
    -0.73
     presentaciones
    -0.73
     насеље
    -0.73
     explanations
    -0.72
     redução
    -0.72
    POSITIVE LOGITS
    曲を
    0.83
     Mueller
    0.79
    Remembering
    0.79
     partition
    0.79
    峽
    0.78
     foil
    0.77
     PVC
    0.77
     Ras
    0.75
     Tank
    0.74
     soil
    0.74
    Activations Density 0.010%

    No Known Activations