© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 54663
    Prev
    Next
    INDEX
    Explanations

    describing states or outcomes

    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
    歎
    0.45
     přij
    0.44
    諄
    0.42
    жде
    0.40
    叹
    0.40
     coldly
    0.39
    
    0.39
     नाइन
    0.38
     nourishing
    0.38
     recapit
    0.38
    POSITIVE LOGITS
    쌈
    0.46
     Freak
    0.45
    lina
    0.44
     Página
    0.44
    ሯ
    0.43
     Lia
    0.43
     detrás
    0.43
    ina
    0.42
     Kennel
    0.42
     aside
    0.42
    Activations Density 0.013%

    No Known Activations