© 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-16K
    7. 985
    Prev
    Next
    INDEX
    Explanations

    kiteconnect

    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
    ค์
    1.16
     sof
    1.01
     plant
    0.97
     abst
    0.97
     tuber
    0.92
     incap
    0.90
     complete
    0.90
    俗
    0.89
     Lei
    0.89
     chino
    0.88
    POSITIVE LOGITS
     vực
    1.47
    hole
    1.36
     pneumoniae
    1.31
    asyon
    1.30
    వలం
    1.29
    apsack
    1.28
    erosene
    1.25
    𒂠
    1.22
     exons
    1.21
    TypeValue
    1.20
    Activations Density 0.512%

    No Known Activations