© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12448
    Prev
    Next
    INDEX
    Explanations

    asking user about their interests

    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
    
    2.02
    ten
    1.98
     हेमा
    1.97
     consider
    1.96
    𝘯
    1.95
     بدان
    1.94
     այ
    1.89
    𝘴
    1.87
    orz
    1.86
    찻
    1.86
    POSITIVE LOGITS
    চ্ছা
    2.29
    aña
    2.20
    ഹു
    2.12
    ኩል
    2.12
     cementing
    2.08
    蒾
    2.05
    ज़ाइन
    2.03
     orphans
    2.02
    jab
    2.01
    añas
    2.01
    Activations Density 0.053%

    No Known Activations