© 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. 222207
    Prev
    Next
    INDEX
    Explanations

    support by

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

    entrepreneurial skills and virtual worlds

    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
    osil
    0.38
    Likewise
    0.38
    ed
    0.38
    正是
    0.38
    риб
    0.37
    縣
    0.36
     dem
    0.36
     destin
    0.35
    FAT
    0.35
    Comput
    0.35
    POSITIVE LOGITS
    लाव
    0.52
    ponses
    0.52
    ณา
    0.52
    LLAR
    0.51
    ្ខ
    0.51
     ওয়
    0.50
    atthe
    0.48
     вопросы
    0.47
    🧸
    0.47
     squeeze
    0.47
    Activations Density 0.000%

    No Known Activations