© 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-RES-262K
    7. 2933
    Prev
    Next
    INDEX
    Explanations

    lack, absence, negation

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ักษณะ
    0.37
    roughly
    0.35
    டுவது
    0.35
    Ⴎ
    0.34
    totalPages
    0.33
    Lore
    0.32
    ળે
    0.32
    ⴼ
    0.32
    ändern
    0.32
     voire
    0.32
    POSITIVE LOGITS
     unfortunately
    0.76
     Unable
    0.74
    残念
    0.74
     unable
    0.73
     Unfortunately
    0.73
     sadly
    0.73
     Sadly
    0.73
     missed
    0.69
     lacked
    0.68
     leider
    0.68
    Activations Density 0.252%

    No Known Activations