© 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. 144473
    Prev
    Next
    INDEX
    Explanations

    jump down

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

    verbs indicating purpose or state

    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
    The
    0.71
     The
    0.70
    the
    0.60
     Create
    0.59
     Some
    0.57
    Some
    0.56
     Creating
    0.56
     Creates
    0.54
    el
    0.54
    A
    0.53
    POSITIVE LOGITS
     glassware
    0.45
     cartão
    0.44
     cartilage
    0.43
     mode
    0.43
     мод
    0.43
     sağlam
    0.43
     bribery
    0.42
     content
    0.42
     دائو
    0.41
     शिलाजीत
    0.41
    Activations Density 0.000%

    No Known Activations