© 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. 14646
    Prev
    Next
    INDEX
    Explanations

    music and code definitions

    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
     अर्जित
    1.72
     athleticism
    1.70
    Synth
    1.65
    Clearly
    1.61
     sauté
    1.61
     frustration
    1.58
    João
    1.56
    🐿
    1.56
    俟
    1.55
     Bolog
    1.55
    POSITIVE LOGITS
    명을
    1.10
    명
    0.99
    тельства
    0.98
    ,
    0.97
    จาก
    0.96
    มาจาก
    0.95
    imleri
    0.95
     from
    0.89
    ي
    0.89
    -
    0.86
    Activations Density 0.102%

    No Known Activations