© 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. 5846
    Prev
    Next
    INDEX
    Explanations

    skiing places

    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
    许多
    0.96
    あなたの
    0.79
    許多
    0.78
     あなた
    0.75
     etcétera
    0.74
    
    0.74
    Qué
    0.73
    ...?
    0.73
    さまざまな
    0.72
    (?)
    0.72
    POSITIVE LOGITS
     upto
    1.37
     atleast
    1.25
     irrespective
    0.99
     inbuilt
    0.95
     =>{
    0.88
     :"
    0.87
     Hence
    0.85
     validations
    0.84
    த்தினை
    0.82
     :-
    0.82
    Activations Density 0.826%

    No Known Activations