© 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. 29215
    Prev
    Next
    INDEX
    Explanations

    technical terms and foreign words

    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
     lymphocytic
    0.51
    කාශ
    0.45
     конди
    0.43
     lymphocytes
    0.42
    ਯ
    0.42
     silvery
    0.42
     vous
    0.42
    uvos
    0.42
    onics
    0.41
    keny
    0.41
    POSITIVE LOGITS
     PrintWriter
    0.47
     '';
    0.45
    ро
    0.44
     Só
    0.43
     utf
    0.42
     Undang
    0.41
     bis
    0.41
    etr
    0.40
     ';
    0.40
    ı
    0.40
    Activations Density 0.001%

    No Known Activations