© 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. 22-GEMMASCOPE-RES-131K
    7. 16705
    Prev
    Next
    INDEX
    Explanations

    Image Quality

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

    It detects bits of technical markup or code—things like HTML-escaped “amp,” file path elements like “directory,” etc.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     adat
    -1.63
     trimestre
    -1.51
     ciclismo
    -1.49
     turista
    -1.43
    　　「
    -1.41
     biodivers
    -1.39
     embri
    -1.38
     eleva
    -1.38
     receive
    -1.38
     in
    -1.38
    POSITIVE LOGITS
     alcune
    1.51
     Этот
    1.40
     zwanzig
    1.39
     Intense
    1.38
     crappy
    1.32
     downloaden
    1.30
     praktisch
    1.29
     REALLY
    1.29
     VERY
    1.28
     diesen
    1.27
    Activations Density 0.001%

    No Known Activations