© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 59997
    Prev
    Next
    INDEX
    Explanations

    numbers and temperature

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

    whole numbers and parts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     trove
    0.55
     recommending
    0.52
    recommended
    0.52
     t
    0.51
    this
    0.51
    row
    0.48
     a
    0.48
    Recommend
    0.48
     
    0.47
      
    0.46
    POSITIVE LOGITS
    ColorBit
    0.59
     மிசோ
    0.58
     Ио
    0.53
    襞
    0.53
    คัญ
    0.52
     градусов
    0.52
     Мари
    0.50
     Фургала
    0.50
    แข็ง
    0.50
    🅴
    0.50
    Activations Density 0.000%

    No Known Activations