© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1959
    Prev
    Next
    INDEX
    Explanations

    applications and applicants

    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
     XNUMX
    1.11
    Ž
    0.76
    ​​
    0.75
    
    0.73
    ↵↵
    0.73
    
    0.72
    itelisted
    0.71
    <0xC2>
    0.71
    (...)
    0.71
    Sh
    0.71
    POSITIVE LOGITS
     সহিত
    1.22
     shortcoming
    1.18
     supposition
    1.12
     gets
    1.08
     maniera
    1.08
     attains
    1.06
     aforesaid
    1.06
     equipments
    1.05
     Gets
    1.04
    的的
    1.04
    Activations Density 0.024%

    No Known Activations