© 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
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 11
    Prev
    Next
    INDEX
    Explanations

    people and quantities

    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_17_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
    이
    1.62
     그리
    1.61
     이어
    1.60
     발전
    1.60
     부분
    1.58
     계획
    1.56
    서
    1.56
     방식
    1.52
     구성
    1.51
     기
    1.51
    POSITIVE LOGITS
    absolutely
    1.90
    relatively
    1.87
    potentially
    1.87
    slightly
    1.85
    possibly
    1.84
    gluten
    1.79
    vegan
    1.77
    adorable
    1.75
    Nicht
    1.73
    typically
    1.73
    Activations Density 0.152%

    No Known Activations