© 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. 70059
    Prev
    Next
    INDEX
    Explanations

    reaching base and patience

    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
     Billing
    -0.76
     fels
    -0.73
     Мер
    -0.72
     HEM
    -0.69
     pimenta
    -0.69
    लय
    -0.68
    移动
    -0.66
    NN
    -0.66
     Styles
    -0.66
     befand
    -0.66
    POSITIVE LOGITS
     reach
    1.42
     reaching
    1.30
     reached
    1.22
     walks
    1.16
     Reaching
    1.16
    Reaching
    1.11
     patience
    1.10
    reach
    1.10
     walk
    1.09
     reaches
    1.09
    Activations Density 0.016%

    No Known Activations