© 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. 53597
    Prev
    Next
    INDEX
    Explanations

    focusing on a specific detail

    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
    (:,
    0.39
    tran
    0.39
    nh
    0.38
    gh
    0.38
    van
    0.38
     HIPAA
    0.38
     VPS
    0.37
    erical
    0.37
    aned
    0.37
     беспо
    0.37
    POSITIVE LOGITS
     toler
    0.46
     capitalization
    0.46
    一日
    0.46
    შ
    0.46
     TECHNI
    0.45
     あっ
    0.45
     consumption
    0.44
     acidity
    0.44
     versatility
    0.44
     Despite
    0.44
    Activations Density 0.006%

    No Known Activations