© 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-16K
    7. 11614
    Prev
    Next
    INDEX
    Explanations

    apologize or promise

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

    apologize or promise

    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_16k_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
    好奇
    0.43
     presumably
    0.40
    identify
    0.40
     адам
    0.40
     menilai
    0.39
    TreeNode
    0.39
    英
    0.39
    鹸
    0.39
    predicate
    0.38
     Hoe
    0.38
    POSITIVE LOGITS
     apologize
    0.81
     apolog
    0.76
     apologise
    0.76
     apologies
    0.75
     apologizing
    0.75
     promise
    0.73
     apology
    0.71
     обеща
    0.68
     promises
    0.67
     Promise
    0.67
    Activations Density 0.352%

    No Known Activations