© 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. 102831
    Prev
    Next
    INDEX
    Explanations

    improving order fulfillment

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

    denying someone's reality

    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
    ANTS
    0.51
    BA
    0.47
    奮
    0.47
    Biography
    0.46
    Parliament
    0.46
    जन्य
    0.46
    ANK
    0.46
    als
    0.45
    ants
    0.45
    MPs
    0.45
    POSITIVE LOGITS
     tecido
    0.51
    beqz
    0.51
     tejido
    0.49
    湿度
    0.47
    잤
    0.47
     cibo
    0.47
     probabilmente
    0.46
     tessuto
    0.46
     problemi
    0.46
     posicao
    0.46
    Activations Density 0.001%

    No Known Activations