© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 13403
    Prev
    Next
    INDEX
    Explanations

    dictionary data structures

    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_17_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
     nibb
    0.84
     steel
    0.82
     agonizing
    0.80
     Steel
    0.80
    =-
    0.79
     Strand
    0.78
    fiber
    0.75
     '/
    0.75
     зуб
    0.75
     Sorrow
    0.74
    POSITIVE LOGITS
     dictionary
    1.36
     Dictionary
    1.23
     dictionaries
    1.22
    字典
    1.17
    toMap
    1.14
     NSDictionary
    1.14
    Dictionary
    1.12
     dicion
    1.11
     словарь
    1.11
    emptyDict
    1.10
    Activations Density 0.561%

    No Known Activations