© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 802
    Prev
    Next
    INDEX
    Explanations

    actions and processes

    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
     เป้า
    0.74
     деб
    0.70
     đạt
    0.67
     squarely
    0.66
    巅峰
    0.66
     পদার্থের
    0.65
     フラ
    0.65
    忑
    0.64
     플러스
    0.63
    進入
    0.63
    POSITIVE LOGITS
     cook
    1.85
     bake
    1.81
     cooked
    1.81
     cooking
    1.78
     brewed
    1.64
     baked
    1.62
    cooking
    1.61
     baking
    1.61
    cooked
    1.59
     выращи
    1.59
    Activations Density 1.591%

    No Known Activations