© 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. 710
    Prev
    Next
    INDEX
    Explanations

    introducing specific 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_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
    等
    0.78
     Và
    0.74
     Однако
    0.73
     및
    0.70
    etc
    0.70
     ומ
    0.68
     आदि
    0.68
    انی
    0.67
    及
    0.66
     وإ
    0.65
    POSITIVE LOGITS
     those
    1.74
     during
    1.59
     with
    1.44
     involving
    1.37
     ones
    1.37
     when
    1.35
     quelli
    1.32
     from
    1.27
     if
    1.26
     in
    1.26
    Activations Density 0.521%

    No Known Activations