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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2634
    Prev
    Next
    INDEX
    Explanations

    phases and stages

    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
     рекорд
    0.61
    ㄹ
    0.60
     العدد
    0.59
     पढ़े
    0.58
    원은
    0.57
    èbres
    0.57
     वैलेंट
    0.57
    呟
    0.57
    원이
    0.56
    olius
    0.56
    POSITIVE LOGITS
     stage
    5.30
     phase
    5.10
     stages
    5.02
     Stage
    4.88
     phases
    4.83
    stage
    4.81
    phase
    4.75
    Stage
    4.70
     Phase
    4.65
    阶段
    4.55
    Activations Density 0.550%

    No Known Activations