© 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. 57115
    Prev
    Next
    INDEX
    Explanations

    Russia and anxiety

    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
    פר
    0.46
    Precision
    0.45
    Ту
    0.44
    Canada
    0.42
    あ
    0.42
    Corporate
    0.42
    рақ
    0.42
    College
    0.41
    Coastal
    0.41
    아
    0.41
    POSITIVE LOGITS
     зао
    0.55
    itch
    0.52
     ruang
    0.50
     ruimte
    0.49
     mirip
    0.47
     bagian
    0.46
     वास्तव
    0.46
     এলাকার
    0.45
     bawa
    0.44
    itiert
    0.44
    Activations Density 0.003%

    No Known Activations