© 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. 25185
    Prev
    Next
    INDEX
    Explanations

    question or topic starter

    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
    Not in Any Lists

    No Comments

    Negative Logits
    werkers
    -1.24
    </code>
    -1.16
    ンピース
    -1.13
    ׂ
    -1.11
     удоволь
    -1.07
     Penh
    -1.05
     opción
    -1.05
     viewDidLoad
    -1.02
    //};
    -1.02
    irut
    -1.01
    POSITIVE LOGITS
     your
    1.93
     you
    1.58
     Pfar
    1.30
     сахара
    1.29
     میکنه
    1.24
     message
    1.21
    醯
    1.16
     byste
    1.16
     máte
    1.14
     ponsel
    1.10
    Activations Density 0.001%

    No Known Activations