© 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. 167768
    Prev
    Next
    INDEX
    Explanations

    portions and dates

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

    keywords followed by context

    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
    價
    0.46
    pflicht
    0.44
    算法
    0.43
    而言
    0.43
    咨
    0.43
     अगस्त
    0.43
    equation
    0.42
    არგ
    0.42
    align
    0.42
    현
    0.42
    POSITIVE LOGITS
     Combined
    0.50
     henüz
    0.50
     Göteborg
    0.50
    шенные
    0.49
     собственной
    0.48
     संयोजन
    0.48
     menina
    0.47
     estudio
    0.47
     années
    0.46
     Ayam
    0.46
    Activations Density 0.001%

    No Known Activations