© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2283
    Prev
    Next
    INDEX
    Explanations

    level of

    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_17_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
    事物
    1.03
     livet
    0.98
    ionati
    0.97
     Bedürfn
    0.95
     घड
    0.95
    쨔
    0.94
     ihtiyaç
    0.93
    anooga
    0.89
     Faktoren
    0.88
    question
    0.87
    POSITIVE LOGITS
     abys
    1.17
    lah
    1.10
    ад
    1.10
     ominous
    1.00
    ಕ್ಕಿಂತ
    1.00
     गोपाल
    0.99
    Edited
    0.99
    ら
    0.98
    ವಿಲ್ಲ
    0.96
    Excess
    0.95
    Activations Density 0.150%

    No Known Activations