© 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. 124667
    Prev
    Next
    INDEX
    Explanations

    other options, information, or services

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

    rates of change or potential growth

    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
     หา
    0.46
    ওয়্যার
    0.46
     Fears
    0.45
     場
    0.45
     May
    0.45
    ]:
    0.44
     మంచి
    0.44
     นิ
    0.44
     کتاب
    0.43
     ทุก
    0.43
    POSITIVE LOGITS
     masts
    0.51
     indigenous
    0.49
     palettes
    0.48
    ي
    0.48
     altri
    0.46
    сім
    0.46
    ıldı
    0.44
     retourner
    0.43
    いや
    0.43
    อื่นๆ
    0.42
    Activations Density 0.000%

    No Known Activations