© 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. 103261
    Prev
    Next
    INDEX
    Explanations

    National Academy Staff Reporter

    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
    乓
    -0.82
    Verizon
    -0.72
    COUNTY
    -0.71
     residencial
    -0.70
     virker
    -0.70
     Elemental
    -0.68
     sagde
    -0.68
     Gonçalves
    -0.68
     €
    -0.66
    سته
    -0.66
    POSITIVE LOGITS
     folha
    0.81
     probablemente
    0.80
     Envío
    0.78
     stattfinden
    0.73
     Bran
    0.73
    ssf
    0.71
     aprendiz
    0.68
    autés
    0.68
     wyma
    0.68
     táo
    0.67
    Activations Density 0.009%

    No Known Activations