© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1930
    Prev
    Next
    INDEX
    Explanations

    bolded text after colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Qu
    0.75
    -
    0.71
     suelos
    0.70
     transcript
    0.69
     Ni
    0.69
    Ᏻ
    0.68
     --
    0.68
     nitrog
    0.68
     пере
    0.66
     toán
    0.65
    POSITIVE LOGITS
     Kritik
    0.82
    passion
    0.74
     électriques
    0.72
    Passion
    0.72
    Factory
    0.72
    嘉
    0.71
     galvan
    0.71
    颧
    0.70
    experiences
    0.70
    lessons
    0.67
    Activations Density 0.295%

    No Known Activations