© 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-65K
    7. 27145
    Prev
    Next
    INDEX
    Explanations

    Race, Theme, tribes, remainder

    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_65k_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
    荩
    0.49
     Rustic
    0.47
     forgo
    0.46
     guarantee
    0.46
     ভা
    0.42
     hospice
    0.41
     oui
    0.40
     yarı
    0.40
     MediaType
    0.39
     remem
    0.39
    POSITIVE LOGITS
    gz
    0.48
    z
    0.45
    venidas
    0.45
    ся
    0.43
    a
    0.42
    brown
    0.42
    ワン
    0.41
    çao
    0.41
     sporad
    0.41
    ंश
    0.41
    Activations Density 0.007%

    No Known Activations