© 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. 219902
    Prev
    Next
    INDEX
    Explanations

    differentiate different product features

    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
     lunch
    0.45
     raft
    0.44
     lunches
    0.42
     adhered
    0.40
     ‘
    0.39
    ˈ
    0.39
     to
    0.38
     treasury
    0.38
    েনে
    0.38
     IN
    0.38
    POSITIVE LOGITS
    汕
    0.41
     toolPath
    0.40
    ローチ
    0.38
    敚
    0.38
     extrapolated
    0.38
    ӹ
    0.37
    ventud
    0.36
    冎
    0.36
    Articulation
    0.36
    untut
    0.35
    Activations Density 0.028%

    No Known Activations