© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1453
    Prev
    Next
    INDEX
    Explanations

    instructions and explanations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
    Whilst
    0.64
     oftentimes
    0.63
     Whilst
    0.56
    Transicao
    0.54
     вследствие
    0.52
     insofar
    0.51
    
    0.51
     તેણી
    0.50
    Supplemental
    0.50
    私たちの
    0.50
    POSITIVE LOGITS
     upto
    0.89
     atleast
    0.79
     :-
    0.75
     apni
    0.75
     betterment
    0.75
     inbuilt
    0.75
     till
    0.73
     wala
    0.73
     aisa
    0.73
     bhi
    0.72
    Activations Density 0.135%

    No Known Activations