© 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. 17560
    Prev
    Next
    INDEX
    Explanations

    logic and inference

    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
    ция
    0.52
    :
    0.48
     upgraded
    0.42
     Standard
    0.42
    3
    0.41
     multilayer
    0.40
    cuits
    0.40
    4
    0.40
    ции
    0.39
     வெளிய
    0.39
    POSITIVE LOGITS
    করিয়
    0.40
    ifah
    0.38
     philanthrop
    0.38
     ابي
    0.38
    ಿಸಬಹುದು
    0.38
     raff
    0.37
     toil
    0.37
     purses
    0.37
     щоб
    0.36
     hens
    0.36
    Activations Density 0.001%

    No Known Activations