© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131752
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    list of ingredients or product filenames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    imleri
    0.50
     sobrevivir
    0.47
     Dull
    0.47
    مس
    0.47
     Todas
    0.46
    籤
    0.45
     Arco
    0.45
    
    0.45
    مد
    0.45
     círculo
    0.45
    POSITIVE LOGITS
     banquet
    0.49
     实现
    0.45
     currency
    0.44
     buttons
    0.44
     platter
    0.44
     dispersion
    0.44
     workstation
    0.44
     onItem
    0.44
     валю
    0.44
     superconducting
    0.43
    Activations Density 0.002%

    No Known Activations