© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 50035
    Prev
    Next
    INDEX
    Explanations

    evacuate or evacuation

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    k
    0.73
    क
    0.62
    ﻛ
    0.59
     WHICH
    0.57
    ซึ่ง
    0.56
     vanishes
    0.55
    UnaryOperation
    0.55
     którego
    0.55
    obedience
    0.54
     disease
    0.53
    POSITIVE LOGITS
     evacuate
    0.65
    楼
    0.64
    樓
    0.64
     evacuation
    0.63
     evac
    0.62
    ë
    0.58
     Gebäude
    0.57
    heed
    0.57
    యితే
    0.55
    伙
    0.53
    Activations Density 0.008%

    No Known Activations