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. 15
    Prev
    Next
    INDEX
    Explanations

    code blocks and comments

    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
     ch
    0.57
    적이
    0.54
     ẞ
    0.53
     won
    0.52
     luk
    0.51
     akadem
    0.49
    ֑
    0.48
     just
    0.48
     sim
    0.48
     les
    0.48
    POSITIVE LOGITS
    ↵↵
    1.62
    ↵↵↵
    1.21
    ↵↵↵↵
    1.17
    ↵↵↵↵↵
    1.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.89
    ↵↵↵↵↵↵
    0.89
    <unused1480>
    0.87
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.87
    ↵↵↵↵↵↵↵↵
    0.87
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.87
    Activations Density 2.339%

    No Known Activations