© 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. 20866
    Prev
    Next
    INDEX
    Explanations

    support your

    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
    nič
    0.54
    ību
    0.54
    çek
    0.50
     acción
    0.50
     İn
    0.50
    could
    0.49
     ойнойт
    0.49
     =====
    0.48
    ícula
    0.47
     мыкты
    0.47
    POSITIVE LOGITS
     vert
    0.43
    劇
    0.43
    時
    0.43
     fumble
    0.43
    量
    0.42
     hearty
    0.41
    血
    0.41
     shapes
    0.41
     favorite
    0.40
    idyl
    0.40
    Activations Density 0.003%

    No Known Activations