© 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. 10536
    Prev
    Next
    INDEX
    Explanations

    preceded by modifiers

    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
    Tcp
    1.01
    歪
    0.99
    жо
    0.98
    ంతరం
    0.98
    โอ
    0.97
    而且
    0.96
     worse
    0.96
    Burst
    0.95
    жим
    0.95
    чайно
    0.94
    POSITIVE LOGITS
     slated
    0.83
     населения
    0.83
     individualized
    0.82
    뻣
    0.81
     endocrine
    0.79
     workforce
    0.78
     residues
    0.78
     NGF
    0.78
     regularmente
    0.78
     bangs
    0.76
    Activations Density 0.000%

    No Known Activations