© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9458
    Prev
    Next
    INDEX
    Explanations

    Large Language

    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_22_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
     প্রসঙ্গে
    1.08
     mentioning
    0.97
     இருப்பதாக
    0.95
    コー
    0.94
     mencion
    0.91
    欤
    0.91
    ައި
    0.89
    であり
    0.89
    攥
    0.89
     ഉണ്ട
    0.88
    POSITIVE LOGITS
     below
    2.34
    below
    2.03
     Below
    1.89
     BELOW
    1.81
     bellow
    1.80
    Below
    1.77
     ниже
    1.48
    以下的
    1.42
     abaixo
    1.42
    以下
    1.40
    Activations Density 0.151%

    No Known Activations