© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13673
    Prev
    Next
    INDEX
    Explanations

    December 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_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
    ㄾ
    2.12
    螂
    2.09
     sprayer
    2.05
     parable
    2.02
    বিত্র
    2.01
    ಹಾಸ
    2.01
    dress
    1.96
    
    1.96
    heast
    1.94
     lesqu
    1.88
    POSITIVE LOGITS
    mu
    1.37
    oxycholic
    1.29
    न्दु
    1.27
    ivatives
    1.25
    conv
    1.25
    توان
    1.25
    amanan
    1.24
    urnal
    1.24
    ঙ্ঘ
    1.22
    hyde
    1.22
    Activations Density 0.038%

    No Known Activations