© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162991
    Prev
    Next
    INDEX
    Explanations

    phrases with 'through the'

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

    listing retail and wholesale

    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
    ins
    0.54
    activ
    0.53
    controlled
    0.52
    organ
    0.49
    у
    0.49
    industrial
    0.49
    activation
    0.48
    classe
    0.48
    fueled
    0.47
    ве
    0.47
    POSITIVE LOGITS
     különböző
    0.48
     بهذا
    0.47
     correttamente
    0.47
     پیغمبر
    0.47
    Bracelet
    0.46
     書き
    0.46
    篇
    0.46
    多个
    0.45
     operandSize
    0.45
     singleArray
    0.45
    Activations Density 0.000%

    No Known Activations