© 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. 16489
    Prev
    Next
    INDEX
    Explanations

    End of sentence or list item indicators

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     refugiados
    -1.34
     Probl
    -1.20
    anstalt
    -1.14
     dedicado
    -1.13
     luxus
    -1.10
     tolua
    -1.10
     soldado
    -1.08
    咂
    -1.08
    搂
    -1.08
    licopter
    -1.06
    POSITIVE LOGITS
    सम
    1.00
    上角
    0.99
     вероятно
    0.97
     seer
    0.94
    у
    0.93
    ipel
    0.93
     kommunizieren
    0.92
    오
    0.91
     notare
    0.91
    <blockquote>
    0.91
    Activations Density 0.571%

    No Known Activations