© 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. 102371
    Prev
    Next
    INDEX
    Explanations

    errors and attempts

    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
     worst
    -0.82
     شاید
    -0.80
     począ
    -0.79
    Unchecked
    -0.79
    我们要
    -0.78
     zupeł
    -0.77
    meros
    -0.76
    Véase
    -0.75
     whatever
    -0.74
     pudieran
    -0.73
    POSITIVE LOGITS
     cannot
    2.45
     нельзя
    2.13
    Cannot
    2.09
    不能
    1.86
    cannot
    1.84
    只能
    1.81
     Cannot
    1.80
     attempted
    1.72
     attempt
    1.67
     attempting
    1.58
    Activations Density 0.042%

    No Known Activations