© 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. 195998
    Prev
    Next
    INDEX
    Explanations

    list ; stainless steel

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

    Chinese and other languages

    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
    มั่น
    0.49
    tough
    0.46
     truthfully
    0.43
     Diem
    0.43
    헉
    0.42
     Mercier
    0.41
    wreck
    0.41
     suppresses
    0.41
    democracy
    0.41
    Glue
    0.41
    POSITIVE LOGITS
    át
    0.58
     pollin
    0.50
    ants
    0.49
    ág
    0.49
    ajt
    0.48
     Zr
    0.48
    ajat
    0.47
    其他
    0.46
    א
    0.46
    দাত
    0.46
    Activations Density 0.001%

    No Known Activations