© 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. 47483
    Prev
    Next
    INDEX
    Explanations

    questions about going upstairs

    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
    Philosophy
    0.44
     tung
    0.42
     @@
    0.41
     hypnotic
    0.37
    tung
    0.36
    交流
    0.36
    notlocked
    0.36
    $`
    0.36
    懺
    0.35
    langle
    0.35
    POSITIVE LOGITS
     проявля
    0.42
     অতিথ
    0.38
    utional
    0.37
    使用的
    0.37
     увагу
    0.37
    玹
    0.37
    提
    0.37
     مث
    0.36
    步
    0.36
    견
    0.36
    Activations Density 0.002%

    No Known Activations