© 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. 10124
    Prev
    Next
    INDEX
    Explanations

    explaining theories

    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
     prag
    1.06
     interventions
    0.96
     decisions
    0.96
     paradox
    0.86
     pragmatic
    0.84
     Decisions
    0.81
     approaches
    0.80
    塑
    0.78
     decision
    0.78
     decisiones
    0.78
    POSITIVE LOGITS
     circulated
    0.84
     menyimpan
    0.84
     fileSize
    0.84
    ंबित
    0.83
    idle
    0.83
     Keep
    0.82
    Keep
    0.82
     Circulation
    0.81
    提交
    0.81
     circula
    0.81
    Activations Density 0.052%

    No Known Activations