© 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. 144663
    Prev
    Next
    INDEX
    Explanations

    immobile immobilization

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

    you've come to

    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
    า
    0.50
    coa
    0.48
    Sandra
    0.46
    2
    0.45
    塔
    0.45
    minute
    0.44
    доро
    0.44
    asa
    0.44
    邵
    0.44
    鬼
    0.43
    POSITIVE LOGITS
     immobile
    0.56
     immobil
    0.55
     jamás
    0.52
     snar
    0.51
     ছিন্ন
    0.51
     immobilization
    0.51
     catap
    0.50
     delimit
    0.49
     imm
    0.48
     Immobil
    0.48
    Activations Density 0.000%

    No Known Activations