© 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. 29075
    Prev
    Next
    INDEX
    Explanations

    internal audit, limited subset

    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
    題目
    0.43
    企業
    0.41
     де
    0.40
     Soll
    0.40
     immobilized
    0.40
    坦
    0.39
    혁
    0.39
    娛樂
    0.39
     एबी
    0.39
    開始
    0.38
    POSITIVE LOGITS
    ından
    0.58
     nakon
    0.54
    ayı
    0.54
     macht
    0.53
     prow
    0.52
     cao
    0.52
    ंधर
    0.51
    k
    0.51
    player
    0.50
    p
    0.50
    Activations Density 0.000%

    No Known Activations