© 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-262K
    7. 14690
    Prev
    Next
    INDEX
    Explanations

    thinking and reasoning processes

    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_262k_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
     oldCount
    0.69
    瑟
    0.67
    attoos
    0.66
     thổ
    0.65
     boilerplate
    0.64
    化妆
    0.64
     tattooing
    0.63
    传输
    0.62
    🥀
    0.62
     tattooed
    0.62
    POSITIVE LOGITS
     cognitive
    2.13
     logic
    2.03
     intellect
    2.02
     thinkers
    2.01
     intellectual
    1.99
     Logic
    1.99
    思维
    1.98
     logical
    1.97
     thinker
    1.94
     brain
    1.94
    Activations Density 0.607%

    No Known Activations