© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153024
    Prev
    Next
    INDEX
    Explanations

    deluxe, deleted, Del, delete

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

    del/delete actions or related words

    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
    Negative Logits
    s
    0.70
    ;
    0.54
     साइकिल
    0.53
     अलविदा
    0.51
    家
    0.51
     category
    0.50
    ulate
    0.50
    СТЬ
    0.50
     deserving
    0.49
     faceted
    0.49
    POSITIVE LOGITS
    DEL
    0.75
     деле
    0.71
    Del
    0.64
     Delaney
    0.63
     Delicate
    0.62
     Delegation
    0.62
     دل
    0.61
     Delight
    0.60
    델
    0.58
    deleted
    0.57
    Activations Density 0.058%

    No Known Activations