© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7137
    Prev
    Next
    INDEX
    Explanations

    rules, criteria, bias

    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
    Your
    0.74
     Investment
    0.74
     কর্ম
    0.71
    opin
    0.70
    持续
    0.70
     your
    0.68
     Consciousness
    0.68
    σ
    0.67
    Healthcare
    0.67
     invested
    0.67
    POSITIVE LOGITS
     criterion
    1.16
     dracon
    1.11
     критери
    1.04
     critères
    0.97
     loophole
    0.96
     discriminatory
    0.96
     criteria
    0.93
     incentivize
    0.90
     requisito
    0.90
     kriter
    0.90
    Activations Density 0.078%

    No Known Activations