© 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. 111463
    Prev
    Next
    INDEX
    Explanations

    little hallway

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

    different seasons

    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
    iras
    0.52
    wearing
    0.50
    u
    0.48
     refine
    0.44
     vog
    0.44
    about
    0.43
    arakhand
    0.43
     quell
    0.42
    ש
    0.41
     cartoon
    0.41
    POSITIVE LOGITS
     নীতিমালা
    0.55
    фесси
    0.51
     XHTML
    0.50
    اضره
    0.49
    জিট
    0.49
     ограничи
    0.49
    ግሎ
    0.47
    矩阵
    0.47
     erred
    0.47
     printr
    0.47
    Activations Density 0.000%

    No Known Activations