© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14879
    Prev
    Next
    INDEX
    Explanations

    crop yields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    셔
    1.83
    ⓢ
    1.62
    嬲
    1.60
    τητας
    1.57
    ಾರಂಭ
    1.54
    活着
    1.53
     Всем
    1.52
    বেশ
    1.51
    ंबर
    1.50
    ℃
    1.49
    POSITIVE LOGITS
     п
    1.68
    ია
    1.56
     attacks
    1.55
     tenor
    1.53
    ifra
    1.49
    اخ
    1.48
     child
    1.48
    avail
    1.48
     outline
    1.48
    isn
    1.47
    Activations Density 0.000%

    No Known Activations