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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 833
    Prev
    Next
    INDEX
    Explanations

    me with prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    ها
    1.42
     itself
    0.99
    هم
    0.95
    它
    0.90
     نفسه
    0.88
    เรา
    0.87
     எங்களுக்கு
    0.86
     уж
    0.83
     తమ
    0.83
    ف
    0.83
    POSITIVE LOGITS
     ايا
    1.55
     personally
    1.46
    zelf
    1.35
    atically
    1.28
     persönlich
    1.28
    倆
    1.21
     personalmente
    1.19
     guys
    1.19
     gái
    1.17
     Personally
    1.15
    Activations Density 0.414%

    No Known Activations