© 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. 144112
    Prev
    Next
    INDEX
    Explanations

    section/part markers

    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
     vídeo
    0.59
     craters
    0.53
    ه
    0.52
     waterfalls
    0.51
     பங்க
    0.49
     Commodities
    0.49
     capsules
    0.49
    Ꮰ
    0.49
     smartphone
    0.49
    し
    0.49
    POSITIVE LOGITS
    .
    0.50
     घात
    0.44
    ermost
    0.44
    หาคม
    0.43
     তোর
    0.41
    andung
    0.41
    ربی
    0.41
    esh
    0.40
    יה
    0.39
    んばんは
    0.38
    Activations Density 0.001%

    No Known Activations