© 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. 68603
    Prev
    Next
    INDEX
    Explanations

    a/an followed by a word

    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
     também
    -1.85
     also
    -1.48
    也很
    -1.41
     también
    -1.38
     также
    -1.30
     anche
    -1.29
     також
    -1.29
     également
    -1.28
     myös
    -1.28
     także
    -1.22
    POSITIVE LOGITS
    atorios
    1.42
    得多
    1.38
     CHARACTERISTICS
    1.25
    therosclerosis
    1.24
    pearance
    1.24
    ſſen
    1.22
    ㇼ
    1.19
    gencias
    1.16
     raggiungere
    1.16
     dragón
    1.16
    Activations Density 0.299%

    No Known Activations