© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7172
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms

    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_22_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
    CONF
    0.99
    }=\{
    0.98
    ℂ
    0.98
     函数
    0.97
    Functions
    0.94
    Nums
    0.92
     Functions
    0.91
    憶
    0.91
    Sph
    0.90
    椭
    0.89
    POSITIVE LOGITS
     pay
    0.97
    pay
    0.97
     Pay
    0.95
     PAY
    0.92
     quedado
    0.90
     fossil
    0.88
     parallax
    0.86
     Jakub
    0.85
    ossil
    0.85
     Ripple
    0.85
    Activations Density 0.015%

    No Known Activations