© 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. 89773
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions or specific words

    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
    তনা
    0.48
     tasas
    0.45
    ه
    0.44
    ινό
    0.44
    зия
    0.43
    izada
    0.43
    েইন
    0.43
     acar
    0.43
    ة
    0.42
     ANOVA
    0.41
    POSITIVE LOGITS
     electing
    0.51
    ClassObject
    0.48
     retiring
    0.48
     presidents
    0.46
     objecting
    0.46
     elected
    0.45
     réfl
    0.43
     dusk
    0.42
     controller
    0.42
    am
    0.42
    Activations Density 0.002%

    No Known Activations