© 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-65K
    7. 56205
    Prev
    Next
    INDEX
    Explanations

    names, generating, providing

    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
    Negative Logits
     Patty
    0.44
     мама
    0.44
     मामा
    0.43
    排出
    0.43
    🐓
    0.42
     giggle
    0.42
     begrü
    0.42
    爸
    0.41
     нала
    0.41
     мать
    0.41
    POSITIVE LOGITS
     using
    0.46
     Fibonacci
    0.46
     Cobalt
    0.42
     사용
    0.41
    使用
    0.40
     کرسک
    0.40
     proposed
    0.39
     containing
    0.39
     Indigo
    0.38
     uży
    0.38
    Activations Density 0.084%

    No Known Activations