© 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. 215983
    Prev
    Next
    INDEX
    Explanations

    feeling of

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

    desire to

    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
     calmed
    0.47
     thawed
    0.44
    nou
    0.44
    क
    0.43
    reda
    0.43
     fontes
    0.42
     obj
    0.41
     avar
    0.41
     oportun
    0.41
    م
    0.41
    POSITIVE LOGITS
    と比較
    0.49
     হলেও
    0.47
     الدراسي
    0.47
     চী
    0.46
    BackgroundTask
    0.45
    Delimiter
    0.45
     элект
    0.44
     Той
    0.43
    вец
    0.43
    enregist
    0.43
    Activations Density 0.001%

    No Known Activations