© 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. 58101
    Prev
    Next
    INDEX
    Explanations

    explanationintroduction for client

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

    passive income

    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
    pH
    0.50
    .[
    0.49
    כ
    0.47
    В
    0.47
    Как
    0.45
    лах
    0.45
    Глав
    0.45
    н
    0.45
    М
    0.45
    解决方法
    0.45
    POSITIVE LOGITS
     tâche
    0.47
     doivent
    0.45
    েও
    0.45
     caster
    0.44
     window
    0.44
     container
    0.43
     peuvent
    0.43
    ূতন
    0.43
     servidor
    0.43
    ောင်
    0.42
    Activations Density 0.000%

    No Known Activations