© 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-262K
    7. 7196
    Prev
    Next
    INDEX
    Explanations

    events and activities

    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_262k_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
    ွား
    0.74
    趁
    0.73
    Pand
    0.72
     обнару
    0.71
     භාවිත
    0.68
    Vacc
    0.68
    戦闘
    0.68
    本次
    0.68
    ീകരിക്ക
    0.68
     vaksin
    0.67
    POSITIVE LOGITS
     során
    0.88
     sırasında
    0.85
     involving
    0.82
    结束后
    0.81
     berlangsung
    0.80
     Spicer
    0.80
    ℗
    0.79
     molestias
    0.79
    ₜ
    0.78
    షణ
    0.78
    Activations Density 0.484%

    No Known Activations