© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225476
    Prev
    Next
    INDEX
    Explanations

    Koenigsegg, settings, morning tea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enjo
    0.50
     enthusi
    0.48
     renormal
    0.48
    %/
    0.47
     fiasco
    0.47
    вью
    0.47
     unamb
    0.46
    ien
    0.46
    expérience
    0.46
     complain
    0.46
    POSITIVE LOGITS
     детский
    0.42
     سمیت
    0.41
    釋
    0.41
    梖
    0.40
    細胞
    0.40
    )’
    0.40
    鉤
    0.40
    摖
    0.40
    院
    0.40
    滤
    0.40
    Activations Density 0.001%

    No Known Activations