© 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. 56668
    Prev
    Next
    INDEX
    Explanations

    hit, take, took, taking

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

    success

    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
    SIL
    0.59
    ﻓ
    0.55
    CHINA
    0.53
    COMPANY
    0.52
    金額
    0.50
    FON
    0.49
    COMP
    0.49
    最後に
    0.49
    ラ
    0.49
    PLUGIN
    0.49
    POSITIVE LOGITS
     synov
    0.55
     lymph
    0.51
     assertions
    0.51
     hamstring
    0.50
     thisComponent
    0.49
     mię
    0.48
     öğren
    0.48
     koş
    0.48
     muscles
    0.47
     ankle
    0.47
    Activations Density 0.000%

    No Known Activations