© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45583
    Prev
    Next
    INDEX
    Explanations

    actions and implications

    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
     histograms
    0.51
     histology
    0.51
     revisited
    0.48
     crystallinity
    0.47
     ensued
    0.46
     Z
    0.45
     alkyl
    0.45
     F
    0.44
     subclasses
    0.44
     Using
    0.43
    POSITIVE LOGITS
     социально
    0.54
    创造
    0.51
    для
    0.49
    Necessary
    0.49
     человеку
    0.47
    做事
    0.47
    стойчи
    0.47
     психологи
    0.47
    众多
    0.46
     necessária
    0.46
    Activations Density 0.013%

    No Known Activations