© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 168133
    Prev
    Next
    INDEX
    Explanations

    move and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ressione
    0.38
     equilíbrio
    0.36
    崠
    0.36
     samen
    0.35
    ल्डर
    0.35
     Nascimento
    0.35
    잎
    0.35
     Equilibrium
    0.34
    boe
    0.34
    俸
    0.34
    POSITIVE LOGITS
     передви
    0.68
     roving
    0.67
     mobility
    0.64
    移動
    0.63
     mobile
    0.59
    移动
    0.59
     이동
    0.59
     travels
    0.57
     roaming
    0.57
     roam
    0.57
    Activations Density 0.022%

    No Known Activations