© 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. 7050
    Prev
    Next
    INDEX
    Explanations

    state transition

    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
    Not in Any Lists

    No Comments

    Negative Logits
     amitié
    -1.35
     листь
    -1.30
    ilige
    -1.30
    
    -1.28
    ᾥ
    -1.27
    ᠌
    -1.24
    НЫХ
    -1.23
    ším
    -1.23
    ЛА
    -1.23
    вшие
    -1.23
    POSITIVE LOGITS
     this
    1.41
    {
    1.40
    яза
    1.40
     wystar
    1.33
     selected
    1.28
     rainha
    1.28
     surpresa
    1.27
    และ
    1.24
     desaparecer
    1.24
    KURZBESCHREIBUNG
    1.23
    Activations Density 0.020%

    No Known Activations