© 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. 14114
    Prev
    Next
    INDEX
    Explanations

    don't even get me started on

    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
    fi
    1.07
     katika
    0.98
     fi
    0.95
     CGC
    0.94
     Petition
    0.93
     พ
    0.93
     Tập
    0.92
     কার্যকলাপ
    0.92
     \|\
    0.92
     \|
    0.91
    POSITIVE LOGITS
    цена
    1.11
    糯
    1.09
    лок
    1.09
     зер
    1.05
    🥯
    1.03
    ટું
    1.01
    .//
    1.01
    meln
    1.01
     தெரிவித்தார்
    1.00
    лке
    1.00
    Activations Density 0.033%

    No Known Activations