© 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. 31-GEMMASCOPE-2-RES-262K
    7. 57078
    Prev
    Next
    INDEX
    Explanations

    segments, segmentation, monitoring, judgments, summary

    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
    لیت
    0.45
    bs
    0.44
     orthogonal
    0.44
     orthogon
    0.44
    블
    0.44
    olecules
    0.44
    گ
    0.43
    Orth
    0.43
    orthogonal
    0.43
    브
    0.42
    POSITIVE LOGITS
     रेटिंग
    0.49
     rejoin
    0.49
     mesaj
    0.47
    ಪಟ್ಟ
    0.47
    ឈ្មោះ
    0.47
    ılığı
    0.46
     fugiat
    0.46
    する
    0.46
     Forester
    0.45
     stari
    0.45
    Activations Density 0.001%

    No Known Activations