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. 8725
    Prev
    Next
    INDEX
    Explanations

    expressing personal actions or feelings

    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
    onym
    -0.97
    orist
    -0.96
    issued
    -0.94
     בישראל
    -0.94
    lla
    -0.94
    zweck
    -0.93
    nothing
    -0.92
    랩
    -0.91
    CHO
    -0.91
    tification
    -0.91
    POSITIVE LOGITS
     doing
    1.91
     done
    1.63
     accomplish
    1.29
     accomplished
    1.27
     Doing
    1.23
     happening
    1.22
     dilakukan
    1.14
     делать
    1.10
    Doing
    1.08
    要做
    1.05
    Activations Density 0.039%

    No Known Activations