© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 215531
    Prev
    Next
    INDEX
    Explanations

    formatting data for tables

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ieve
    0.49
    वर्स
    0.42
    डेंट
    0.40
    ipc
    0.40
    Scenario
    0.39
    тивное
    0.39
    எ
    0.39
    Campbell
    0.38
    ere
    0.38
    Files
    0.38
    POSITIVE LOGITS
     vil
    0.43
     garnished
    0.43
     сначала
    0.41
     jalap
    0.41
    ecake
    0.41
     decline
    0.40
     lemak
    0.40
     লিল
    0.40
     gon
    0.39
    襖
    0.38
    Activations Density 0.001%

    No Known Activations