© 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. 49570
    Prev
    Next
    INDEX
    Explanations

    DB Link schema

    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
    协作
    0.47
     trasferimento
    0.44
     bater
    0.42
     apologise
    0.41
    窨
    0.41
     apologised
    0.40
     batteries
    0.40
     Batteries
    0.40
    Battery
    0.39
    Inspector
    0.39
    POSITIVE LOGITS
     Proc
    0.57
     PN
    0.54
    PN
    0.53
    Proc
    0.52
    proc
    0.48
     सोने
    0.42
     proc
    0.41
     "["
    0.41
     დარ
    0.40
     PROC
    0.39
    Activations Density 0.008%

    No Known Activations