© 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. 5114
    Prev
    Next
    INDEX
    Explanations

    connecting clauses and lists

    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
    ,
    1.21
    :
    1.00
    -
    0.96
    ،
    0.90
    In
    0.84
    ?
    0.82
    ，
    0.82
     ،
    0.80
    ...
    0.79
    Whatever
    0.79
    POSITIVE LOGITS
     which
    2.00
     although
    1.86
     waarbij
    1.79
     obwohl
    1.68
     whereby
    1.65
     though
    1.64
     takže
    1.61
     który
    1.57
     whereupon
    1.57
     jotka
    1.56
    Activations Density 0.238%

    No Known Activations