© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202323
    Prev
    Next
    INDEX
    Explanations

    designed, definitive, rating, ROI

    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_31_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
     moiety
    0.45
     composite
    0.41
     participle
    0.40
     составля
    0.40
    这
    0.40
     Composite
    0.40
     τόσο
    0.39
     বাঁ
    0.39
     প্রবন্ধ
    0.39
    Study
    0.39
    POSITIVE LOGITS
    ೀನ
    0.45
    江湖
    0.43
    믿
    0.43
    埌
    0.42
     markets
    0.41
    ChooseCharacter
    0.41
     mercados
    0.41
    ਲ
    0.41
     announc
    0.40
    जे
    0.40
    Activations Density 0.006%

    No Known Activations