© 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. 38545
    Prev
    Next
    INDEX
    Explanations

    wordpress

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    u
    -4.03
    ing
    -3.16
    न
    -3.14
     ใน
    -3.09
    .'
    -2.91
    .”
    -2.89
    }$,
    -2.83
    on
    -2.78
     In
    -2.66
     \%$,
    -2.53
    POSITIVE LOGITS
    sach
    2.52
     poissons
    2.45
     elástico
    2.44
     angebra
    2.38
    を作り
    2.38
     vegano
    2.36
     bordada
    2.36
    0
    2.34
     parachoque
    2.33
     luminoso
    2.31
    Activations Density 0.004%

    No Known Activations