© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99650
    Prev
    Next
    INDEX
    Explanations

    humanity, society, and liking

    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
    ма
    0.43
    다
    0.43
    डे
    0.42
     happen
    0.41
    ინი
    0.41
     poisoned
    0.41
    ने
    0.41
     пона
    0.40
     dono
    0.40
    ڈر
    0.40
    POSITIVE LOGITS
     utilisons
    0.56
    ovou
    0.53
     utilisent
    0.52
    藜
    0.51
     plufieurs
    0.50
    tomorrow
    0.50
     allemand
    0.50
     échanc
    0.49
     espaces
    0.49
     ombil
    0.47
    Activations Density 0.004%

    No Known Activations