© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15568
    Prev
    Next
    INDEX
    Explanations

    hyperhomocysteinaemia

    np_acts-logits-general · gemini-2.5-flash-lite

    punctuation marks like commas and colons followed by explanatory content in academic or technical writing.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     сал
    -1.10
     turista
    -1.02
     części
    -1.02
    はこの
    -1.00
    鹛
    -0.98
     maniere
    -0.96
    這
    -0.96
    ној
    -0.95
    gevens
    -0.95
     frapp
    -0.94
    POSITIVE LOGITS
     any
    1.38
     ANY
    1.30
     that
    1.27
     and
    1.16
     sowie
    1.13
    三种
    1.13
     exclusivas
    1.13
    じゃあ
    1.13
     which
    1.13
     cualquier
    1.13
    Activations Density 0.158%

    No Known Activations