© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1084
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and optimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    Cost
    0.69
    All
    0.68
    стры
    0.67
    Elegant
    0.67
    દ્
    0.66
    ᥙ
    0.64
    Tasty
    0.64
    람
    0.64
    Concept
    0.64
    Taste
    0.64
    POSITIVE LOGITS
     minimizing
    0.70
     seventh
    0.66
     sixth
    0.64
     dismantling
    0.60
     maximizing
    0.59
     ninth
    0.58
     Maharashtra
    0.58
     மறை
    0.57
     abertura
    0.56
     Seventh
    0.56
    Activations Density 0.367%

    No Known Activations