© 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. 5689
    Prev
    Next
    INDEX
    Explanations

    model, asset, traders, language

    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
     the
    0.39
     a
    0.39
    0.39
    தாவது
    0.35
     sandy
    0.35
     an
    0.34
     this
    0.33
     bush
    0.33
     squat
    0.33
     CMake
    0.32
    POSITIVE LOGITS
    ที่มี
    0.44
    であり
    0.41
    Κ
    0.39
    សម្រាប់
    0.39
     импе
    0.38
     andRow
    0.38
    很多人
    0.37
     inasmuch
    0.37
     zarówno
    0.37
    ígeno
    0.36
    Activations Density 0.078%

    No Known Activations