© 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. 36935
    Prev
    Next
    INDEX
    Explanations

    difficulty, formation, score

    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
    yrıca
    0.45
     bruge
    0.43
    Então
    0.42
     nagyon
    0.42
     verdade
    0.42
     produk
    0.41
     بہت
    0.41
    贬
    0.40
     recuperação
    0.40
    伤害
    0.40
    POSITIVE LOGITS
     only
    0.42
    only
    0.42
     June
    0.42
    sys
    0.41
     Completed
    0.41
     Selected
    0.40
     Hamiltonian
    0.40
     Frontiers
    0.39
     excluded
    0.38
     Directive
    0.38
    Activations Density 0.022%

    No Known Activations