© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 3732
    Prev
    Next
    INDEX
    Explanations

    texture size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     Gynecol
    0.41
     Decomposition
    0.40
    饉
    0.38
     Oats
    0.38
    قول
    0.37
     Groundwater
    0.37
     Trench
    0.37
     Corruption
    0.37
     Polymers
    0.36
     Syndrome
    0.36
    POSITIVE LOGITS
     отобра
    0.40
    /
    0.40
     tersebut
    0.40
     mendapatkan
    0.39
     darstellen
    0.38
      
    0.38
     त्यांनी
    0.38
     tarafından
    0.37
     они
    0.37
     mereka
    0.37
    Activations Density 0.165%

    No Known Activations