© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23734
    Prev
    Next
    INDEX
    Explanations

    too good

    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
    thmus
    -0.79
    ajoz
    -0.78
     млрд
    -0.78
    ripsi
    -0.78
     obce
    -0.76
    𝙁
    -0.76
    leun
    -0.75
    omena
    -0.73
    нав
    -0.73
    lanti
    -0.72
    POSITIVE LOGITS
     superior
    2.77
    superior
    2.45
     superiority
    1.95
    Superior
    1.79
     Superior
    1.77
     superiores
    1.67
     superiore
    1.64
     SUPERIOR
    1.60
     supérieure
    1.42
     above
    1.40
    Activations Density 0.043%

    No Known Activations