© 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. 165209
    Prev
    Next
    INDEX
    Explanations

    leader, weddings, businesses

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

    desire for options

    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
    視
    0.49
    Tìm
    0.47
    -"
    0.47
    recer
    0.46
     phận
    0.46
    तीश
    0.46
     پای
    0.45
     দাঁড়
    0.44
    dal
    0.44
     trời
    0.43
    POSITIVE LOGITS
    mV
    0.47
    etre
    0.44
    etta
    0.43
     bloodshed
    0.43
    桷
    0.43
    mW
    0.42
     snelheid
    0.42
     blod
    0.42
    DER
    0.41
     ആക്രമ
    0.41
    Activations Density 0.001%

    No Known Activations