© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4220
    Prev
    Next
    INDEX
    Explanations

    acronyms and initialisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     sorgt
    0.97
     ਖ
    0.93
     البته
    0.91
     niektor
    0.90
    instead
    0.89
    unlike
    0.89
     eingesetzt
    0.89
     jakości
    0.88
     aufgrund
    0.88
     送料無料
    0.87
    POSITIVE LOGITS
     ad
    0.87
      
    0.81
     l
    0.81
     A
    0.79
     From
    0.79
     No
    0.76
     command
    0.74
     middle
    0.73
     pr
    0.72
     Third
    0.71
    Activations Density 0.052%

    No Known Activations