© 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. 15654
    Prev
    Next
    INDEX
    Explanations

    efficiency, rate, orally, out, R

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

    words related to measurement and rates like "efficiency", "rate", "ruler", and numerical values.

    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
     Technically
    -2.48
     Lately
    -2.48
    uminazione
    -2.44
     เพราะ
    -2.33
     Roughly
    -2.30
     Effectively
    -2.30
     Traditionally
    -2.28
     Gebiete
    -2.22
     Because
    -2.22
     Ironically
    -2.17
    POSITIVE LOGITS
    2
    2.77
    J
    2.63
    也在
    2.58
    of
    2.58
    la
    2.56
    le
    2.56
     nuovo
    2.53
    son
    2.52
    _
    2.48
    Ꮔ
    2.48
    Activations Density 0.002%

    No Known Activations