© 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. 8631
    Prev
    Next
    INDEX
    Explanations

    options and qualities

    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
     Box
    0.43
     props
    0.42
    ポーチ
    0.42
    ও
    0.40
    unused
    0.40
     leftover
    0.40
     box
    0.39
    props
    0.39
     Alkaline
    0.39
     ridge
    0.38
    POSITIVE LOGITS
    𝗯
    0.47
    idence
    0.46
     diberi
    0.45
     инструмента
    0.43
    цами
    0.42
    beda
    0.41
    IT
    0.41
    erà
    0.41
    ціона
    0.41
    hmad
    0.41
    Activations Density 0.008%

    No Known Activations