© 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. 51884
    Prev
    Next
    INDEX
    Explanations

    dealt with serious themes

    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
     tweet
    0.45
     walnuts
    0.42
     qualche
    0.41
    瞌
    0.41
     εφ
    0.41
    ウォー
    0.40
     টুই
    0.39
    Questions
    0.39
     tweeted
    0.39
    WAL
    0.39
    POSITIVE LOGITS
    注
    0.42
     DeepCollection
    0.41
    普及
    0.39
    Fully
    0.39
    क्षात्कार
    0.39
    믿
    0.39
     믿
    0.38
    ეგის
    0.38
     fully
    0.38
     vast
    0.37
    Activations Density 0.001%

    No Known Activations