Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8722
    Prev
    Next
    INDEX
    Explanations

    email 'sent:' line

    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
    彦
    -0.87
    Tab
    -0.83
    backgroundImage
    -0.79
     космети
    -0.77
     may
    -0.76
    adins
    -0.75
    暑假
    -0.74
    /*---
    -0.73
    __(
    -0.71
    вушка
    -0.71
    POSITIVE LOGITS
    Kamer
    0.82
    pentry
    0.81
    obiety
    0.81
     liberar
    0.80
     davanti
    0.80
    ldon
    0.79
     fiabilidad
    0.79
    🍶
    0.79
     restructure
    0.79
     ジュニア
    0.79
    Activations Density 0.001%

    No Known Activations