© 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. 22-GEMMASCOPE-2-RES-16K
    7. 4049
    Prev
    Next
    INDEX
    Explanations

    various relationships and context

    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_22_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
    鬧
    0.82
    闹
    0.80
    undered
    0.76
    Contributing
    0.69
    panic
    0.69
     標準
    0.68
    controls
    0.67
    орк
    0.67
     नॉलेज
    0.67
    곰
    0.66
    POSITIVE LOGITS
    并行
    0.61
     allerlei
    0.61
     berbagai
    0.59
    ябре
    0.58
    异步
    0.58
     माप
    0.58
    ovac
    0.57
     similarities
    0.57
     località
    0.57
     mesure
    0.57
    Activations Density 0.140%

    No Known Activations