© 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. 17-GEMMASCOPE-2-RES-16K
    7. 212
    Prev
    Next
    INDEX
    Explanations

    depends on conditions

    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_17_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
    。
    0.45
    。(
    0.43
    。.
    0.43
     כאשר
    0.42
    $.
    0.41
    .(
    0.40
    ۔
    0.39
     以及
    0.39
     Ал
    0.39
     cuando
    0.38
    POSITIVE LOGITS
     depends
    0.64
     varies
    0.64
     differs
    0.56
     fluctuates
    0.56
     goes
    0.53
     comes
    0.50
     relies
    0.50
     hasn
    0.50
     lingers
    0.49
     diminishes
    0.48
    Activations Density 0.502%

    No Known Activations