© 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. 46050
    Prev
    Next
    INDEX
    Explanations

    one-shot enemies; Australians

    np_acts-logits-general · gemini-2.5-flash-lite

    breaks, getaways, or plans

    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
    questa
    0.41
     Curator
    0.40
    spacing
    0.40
     Detect
    0.40
    ORF
    0.40
     器
    0.39
    ighter
    0.39
    龛
    0.39
    场的
    0.38
     Imper
    0.38
    POSITIVE LOGITS
     stuffs
    0.41
     deewana
    0.41
     Пари
    0.39
     rallying
    0.39
     хар
    0.38
    냈다
    0.38
     secrete
    0.37
    와이스
    0.37
     nhật
    0.37
    ውነ
    0.37
    Activations Density 0.000%

    No Known Activations