© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5086
    Prev
    Next
    INDEX
    Explanations

    programming code components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ophenyl
    0.96
    ethyl
    0.87
    utsch
    0.86
    Lastly
    0.85
    ơ
    0.83
    我们也
    0.83
    if
    0.83
    כו
    0.83
    Then
    0.81
     उसी
    0.79
    POSITIVE LOGITS
     ///<
    0.80
    тат
    0.74
     readonly
    0.72
     constructor
    0.68
     Accepts
    0.67
     Gets
    0.67
    可以是
    0.66
     sahiptir
    0.66
     CRUD
    0.66
     MOQ
    0.65
    Activations Density 0.192%

    No Known Activations