© 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. 12-GEMMASCOPE-2-RES-262K
    7. 7604
    Prev
    Next
    INDEX
    Explanations

    numbers or non-English characters

    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_12_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
    ️⃣
    0.30
    ⃣
    0.29
    inė
    0.29
    am
    0.29
    al
    0.28
    ாய
    0.28
    in
    0.27
    。（
    0.27
    க்கொண்ட
    0.27
    ান
    0.27
    POSITIVE LOGITS
    Та
    0.36
    आई
    0.36
    РА
    0.34
    2
    0.34
    3
    0.32
    1
    0.32
    س
    0.31
    4
    0.31
    및
    0.31
    और
    0.29
    Activations Density 0.169%

    No Known Activations