© 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. 40-GEMMASCOPE-2-RES-262K
    7. 210192
    Prev
    Next
    INDEX
    Explanations

    perfect squares

    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_40_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
     defy
    0.42
     Cinderella
    0.41
     Circuits
    0.40
     Joan
    0.40
     apud
    0.39
     rumors
    0.39
     Crem
    0.38
    </bbox>
    0.38
     primary
    0.37
     ether
    0.37
    POSITIVE LOGITS
    完璧
    0.53
    RowNum
    0.50
    Perfect
    0.48
     perfetta
    0.47
     perfecta
    0.47
     मोहो
    0.46
    完美
    0.45
     perfeita
    0.44
    perfect
    0.43
     cuadrados
    0.43
    Activations Density 0.002%

    No Known Activations