© 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-65K
    7. 5137
    Prev
    Next
    INDEX
    Explanations

    counting, summing, and averaging values

    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
     hostage
    0.65
     negotiators
    0.62
    谈判
    0.62
     procéd
    0.62
    évrier
    0.62
     तलवार
    0.61
     தொட
    0.61
    雾
    0.60
     interven
    0.60
    θέ
    0.60
    POSITIVE LOGITS
     count
    2.89
     counts
    2.86
    counts
    2.76
     counting
    2.69
    count
    2.67
    Counts
    2.67
     Counting
    2.61
    统计
    2.60
     Counts
    2.58
    Counting
    2.58
    Activations Density 0.758%

    No Known Activations