© 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. 68711
    Prev
    Next
    INDEX
    Explanations

    commerce and travel data

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

    wrapped with, tucked into, intent, wait on

    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
     garage
    0.54
     dépasse
    0.49
    核心
    0.48
     sed
    0.47
    garage
    0.47
    葷
    0.46
    팎
    0.46
     seminal
    0.46
     tenure
    0.45
    地域の
    0.45
    POSITIVE LOGITS
    াস্ত
    0.47
    ករ
    0.47
     நிமிடங்கள்
    0.45
    CAG
    0.43
    THERE
    0.43
    ില
    0.41
     резер
    0.41
    ష
    0.40
     ష
    0.40
    SECURITY
    0.40
    Activations Density 0.001%

    No Known Activations