© 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. 125935
    Prev
    Next
    INDEX
    Explanations

    intricate internal structures

    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
    з
    0.48
    .«
    0.46
    ان
    0.43
    㐫
    0.43
     σου
    0.41
    Height
    0.41
    Salah
    0.41
    Stef
    0.41
    蹺
    0.41
    ন
    0.40
    POSITIVE LOGITS
     จึง
    0.53
     دقیق
    0.50
     วัน
    0.49
     दर्पण
    0.48
     필요
    0.47
     มี
    0.47
     라이
    0.47
     variabel
    0.47
     necessari
    0.46
     microfilm
    0.46
    Activations Density 0.007%

    No Known Activations