© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9535
    Prev
    Next
    INDEX
    Explanations

    let cool or sit

    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
    ESSITY
    1.54
     τὴν
    1.50
     是
    1.48
    ה
    1.42
    𝘯
    1.39
     ND
    1.38
    GLE
    1.38
     Рим
    1.38
    tos
    1.37
     DI
    1.36
    POSITIVE LOGITS
    Attrition
    1.94
    ح
    1.89
    ypen
    1.88
    𝚢
    1.87
    ้าง
    1.85
    ahul
    1.84
    iany
    1.80
    ových
    1.79
    راق
    1.76
    ékony
    1.76
    Activations Density 0.023%

    No Known Activations