© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 684
    Prev
    Next
    INDEX
    Explanations

    structure</br>proteins

    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
    S
    0.64
    Г
    0.64
    ่
    0.62
     Lưu
    0.62
    H
    0.62
    J
    0.62
    W
    0.61
    G
    0.59
    ი
    0.57
    п
    0.56
    POSITIVE LOGITS
     την
    0.98
     που
    0.96
     også
    0.92
     από
    0.91
     στην
    0.88
     anche
    0.87
     edhe
    0.86
     της
    0.86
     các
    0.86
     కూడా
    0.85
    Activations Density 0.527%

    No Known Activations