© 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
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2849
    Prev
    Next
    INDEX
    Explanations

    for a linked list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OfThe
    1.11
    Something
    1.00
     ofthe
    0.90
     τον
    0.88
    ForThe
    0.86
    ethe
    0.86
    蠵
    0.84
     atthe
    0.84
    Another
    0.84
    Someone
    0.82
    POSITIVE LOGITS
    <unused2197>
    0.75
     indeed
    0.72
     zowel
    0.66
     both
    0.64
      
    0.64
     Ein
    0.59
     primarily
    0.58
     并
    0.58
    <unused2169>
    0.58
    indeed
    0.58
    Activations Density 0.173%

    No Known Activations