© 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-65K
    4. 40111
    Prev
    Next
    INDEX
    Explanations

    descriptions of states and actions

    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
    𝐞
    0.51
    𝘦
    0.50
     ස්
    0.50
     بسیاری
    0.50
     sensação
    0.50
     scrivere
    0.49
     부정
    0.48
    cual
    0.48
     cinque
    0.47
    𝚎
    0.47
    POSITIVE LOGITS
     imports
    0.49
     harnesses
    0.46
     boxes
    0.46
     fuels
    0.46
     traps
    0.45
    क्त
    0.45
    АК
    0.45
     items
    0.45
     encapsulates
    0.45
     stands
    0.44
    Activations Density 0.002%

    No Known Activations