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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 16191
    Prev
    Next
    INDEX
    Explanations

    contractions like dont isnt arent

    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
     (“
    1.34
     “
    1.24
     (
    1.10
      
    1.08
     ("
    1.07
     "
    1.06
     ‘
    1.03
    <0xE2>
    1.00
     “(
    1.00
     (‘
    1.00
    POSITIVE LOGITS
     nbsp
    1.48
     youll
    1.28
     doesnt
    1.22
     Dont
    1.20
     Thats
    1.20
     dont
    1.18
     isnt
    1.14
     arent
    1.14
     didnt
    1.14
     wasnt
    1.09
    Activations Density 0.047%

    No Known Activations