© 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. 106403
    Prev
    Next
    INDEX
    Explanations

    creation or transaction

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

    words before "signing" or "transform" or "let's"

    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
     estrat
    0.51
     indiquer
    0.49
     desconocido
    0.48
     Reserva
    0.47
     camadas
    0.46
     adatto
    0.45
     তা
    0.45
    ξη
    0.45
    ا
    0.44
    خير
    0.44
    POSITIVE LOGITS
     copil
    0.47
    ériment
    0.45
     판매
    0.44
     सप्लाई
    0.43
     स्वामित्व
    0.43
    㴦
    0.43
     உருவாக்கு
    0.42
    '%(
    0.42
    çay
    0.41
     소비자
    0.40
    Activations Density 0.001%

    No Known Activations