© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1098
    Prev
    Next
    INDEX
    Explanations

    instructions and guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     изначально
    0.82
    😔
    0.79
    称
    0.78
    ดังกล่าว
    0.77
    該当
    0.75
    ↓
    0.75
     해당
    0.74
    ได้
    0.73
     ※
    0.73
    ას
    0.73
    POSITIVE LOGITS
     Handbook
    1.99
    Handbook
    1.87
     handbook
    1.87
     Essays
    1.77
     Wege
    1.70
     concise
    1.69
     Principles
    1.67
     Adventures
    1.66
     Biographical
    1.64
     Anleitung
    1.63
    Activations Density 0.930%

    No Known Activations