© 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. 14796
    Prev
    Next
    INDEX
    Explanations

    historical periods and dates

    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
     Bugünkü
    1.85
    häuse
    1.83
     አይነት
    1.83
     prácticamente
    1.82
     Gazetteer
    1.82
     Lieut
    1.80
     İş
    1.78
    Ә
    1.76
     Ejército
    1.76
     Qualquer
    1.75
    POSITIVE LOGITS
     medications
    1.81
     learners
    1.70
     adolescents
    1.70
     edema
    1.70
     insecurity
    1.69
     insecurities
    1.69
     stressors
    1.64
     arrhythmia
    1.64
     serotonin
    1.64
     babys
    1.61
    Activations Density 0.064%

    No Known Activations