© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7597
    Prev
    Next
    INDEX
    Explanations

    microsoft.com/en-us links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     Hause
    0.98
    RouterProvider
    0.97
    anging
    0.96
    мер
    0.94
    ۃ
    0.93
    awca
    0.92
    箇所
    0.91
    सिव
    0.91
    嵘
    0.91
    行政
    0.90
    POSITIVE LOGITS
     fountain
    0.88
     झा
    0.86
     chis
    0.83
    symbol
    0.81
    ֿ
    0.80
     figures
    0.80
     аба
    0.79
     그림
    0.79
    OAc
    0.79
    İK
    0.78
    Activations Density 0.003%

    No Known Activations