© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1258
    Prev
    Next
    INDEX
    Explanations

    Precisely, anomalies

    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_13_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
     mindset
    1.96
     showcasing
    1.92
     impactful
    1.91
    ⁣
    1.85
     generando
    1.71
    ​​​​
    1.68
     leveraging
    1.68
     relatable
    1.66
    ✅
    1.62
     بشكل
    1.61
    POSITIVE LOGITS
    明年
    1.35
    只好
    1.34
    燗
    1.32
    irthday
    1.32
    튿
    1.31
    (")
    1.30
    !:
    1.29
    ="(
    1.28
    엷
    1.27
    ubercul
    1.27
    Activations Density 1.096%

    No Known Activations