© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 42462
    Prev
    Next
    INDEX
    Explanations

    Quantization Aware Training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
     garages
    0.52
     patios
    0.52
    }}\|
    0.48
    teur
    0.47
    ગાહી
    0.46
    nominated
    0.46
    ຈັດສົ່ງ
    0.45
     autoclave
    0.45
    tection
    0.45
    stoke
    0.45
    POSITIVE LOGITS
    、
    0.54
    ป
    0.50
     первый
    0.48
     sebab
    0.47
     murderer
    0.47
     perdió
    0.47
     ڏ
    0.47
     réponse
    0.46
    パン
    0.46
    了
    0.46
    Activations Density 0.000%

    No Known Activations