© 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. 36916
    Prev
    Next
    INDEX
    Explanations

    historical context or traditional methods

    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
     turut
    0.55
     take
    0.49
     embark
    0.45
    镳
    0.44
    рафон
    0.42
    Take
    0.41
     afecta
    0.40
     restre
    0.40
     prendere
    0.39
    ح
    0.39
    POSITIVE LOGITS
     외부
    0.54
     ছাড়
    0.51
     свойств
    0.50
    <0x80>
    0.50
     మి
    0.48
     వచ్చ
    0.48
     સ્ક
    0.46
     मिट्टी
    0.46
     equidistant
    0.46
    외부
    0.46
    Activations Density 0.013%

    No Known Activations