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-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 3683
    Prev
    Next
    INDEX
    Explanations

    up-to-date information

    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
    这两个
    0.59
    വ്യ
    0.56
    过去了
    0.54
     कठ
    0.54
     zwier
    0.54
     chcia
    0.54
    みたいな
    0.53
    蘑
    0.53
     फि
    0.53
     inten
    0.52
    POSITIVE LOGITS
    罟
    0.74
    uttab
    0.71
    ែក
    0.69
    туи
    0.68
    decode
    0.64
     Canaan
    0.63
    ন্দন
    0.63
     լ
    0.62
     Lisbon
    0.61
     harnesses
    0.61
    Activations Density 0.150%

    No Known Activations