© 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-65K
    7. 841
    Prev
    Next
    INDEX
    Explanations

    liquid substances and their combinations

    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_65k_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
    Nodes
    1.08
     информа
    0.91
    观测
    0.87
    Blockchain
    0.86
     ejecución
    0.86
     ബന്ധ
    0.85
     observability
    0.85
    峋
    0.85
    Architecture
    0.85
    节点
    0.85
    POSITIVE LOGITS
     liquid
    2.55
     liquids
    2.49
     syrup
    2.26
     aqueous
    2.22
     diluted
    2.10
     fluids
    2.07
    液体
    2.04
     vinegar
    2.04
    liquid
    2.02
     Liquid
    2.00
    Activations Density 0.717%

    No Known Activations