© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 111
    Prev
    Next
    INDEX
    Explanations

    data reflecting biases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     నగ
    0.51
    ఎఫ్
    0.48
    Quaternion
    0.47
     промышленности
    0.46
    Gol
    0.44
    ан
    0.44
    Ƒ
    0.43
    Punj
    0.43
     स्वरों
    0.43
    খ্য
    0.42
    POSITIVE LOGITS
    ed
    0.41
    น
    0.41
    वे
    0.40
     dodgy
    0.40
    isez
    0.40
    vem
    0.40
    न
    0.40
    ('\
    0.39
    ISHED
    0.39
     ​​
    0.38
    Activations Density 0.006%

    No Known Activations