© 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. 102607
    Prev
    Next
    INDEX
    Explanations

    list of

    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
    Scar
    -0.81
     intérêt
    -0.77
    Crazy
    -0.76
    elope
    -0.75
    cestershire
    -0.74
    дом
    -0.74
     wedstrijd
    -0.74
    Ez
    -0.74
    Lett
    -0.73
     skar
    -0.73
    POSITIVE LOGITS
     barro
    0.86
    しつつ
    0.85
    citet
    0.80
    omez
    0.79
    éter
    0.77
     друго
    0.77
     Städ
    0.77
    itzender
    0.76
    after
    0.75
    тника
    0.75
    Activations Density 0.037%

    No Known Activations