© 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. 1498
    Prev
    Next
    INDEX
    Explanations

    DeepMind

    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
     ‘
    1.89
    臾
    1.81
    ティック
    1.79
     '
    1.77
    ƌ
    1.77
    CHEMY
    1.73
     jong
    1.66
    ↵
    1.64
    δήποτε
    1.58
    꿍
    1.54
    POSITIVE LOGITS
    সূত্র
    2.21
     ifstream
    2.11
    覦
    2.07
    𝚎
    2.06
    lemma
    1.98
     Loops
    1.98
    ぇ
    1.97
    谍
    1.95
     Yukawa
    1.94
     mutter
    1.93
    Activations Density 0.122%

    No Known Activations