© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6241
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and problem solving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     math
    0.77
     corral
    0.75
     Riemann
    0.73
     당신
    0.71
     mathematically
    0.70
     renormalized
    0.70
     inverses
    0.70
    𝟙
    0.69
     orthogonality
    0.69
     summand
    0.68
    POSITIVE LOGITS
     Paryayvachi
    0.89
     Gandhiji
    0.88
     Rajput
    0.87
     Paytm
    0.87
     salwar
    0.84
     inbuilt
    0.82
    apayati
    0.82
     Jharkhand
    0.80
    hitva
    0.79
     Odisha
    0.79
    Activations Density 0.227%

    No Known Activations