© 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. 2713
    Prev
    Next
    INDEX
    Explanations

    even further

    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
     myriad
    0.71
     disparate
    0.66
    <0xE2>
    0.63
     those
    0.62
     (’
    0.61
     commonplace
    0.58
     heavily
    0.58
     tod
    0.58
     wholly
    0.57
     ful
    0.57
    POSITIVE LOGITS
     sodass
    0.99
     nedeniyle
    0.94
    برای
    0.94
    while
    0.90
     gdyż
    0.89
    Très
    0.88
    ♡
    0.86
    png
    0.86
     ज़कात
    0.85
     deoarece
    0.85
    Activations Density 0.139%

    No Known Activations