© 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. 83611
    Prev
    Next
    INDEX
    Explanations

    doing and done

    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
    ımıza
    -0.99
     tejto
    -0.90
    ṓ
    -0.88
    Vlast
    -0.86
    蠔
    -0.85
    autés
    -0.83
    中です
    -0.82
     Traverse
    -0.82
     eingeladen
    -0.82
    Ava
    -0.81
    POSITIVE LOGITS
     doing
    5.28
    Doing
    4.44
    doing
    4.25
     Doing
    4.06
     done
    2.95
    做
    2.86
     DOING
    2.73
     doin
    2.56
     делать
    2.52
     do
    2.44
    Activations Density 0.098%

    No Known Activations