© 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. 34-GEMMASCOPE-RES-131K
    7. 79217
    Prev
    Next
    INDEX
    Explanations

    this source code

    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_34/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
    使用
    -1.42
     using
    -1.35
     sử
    -1.19
     usage
    -1.08
    using
    -1.07
     menggunakan
    -1.02
     usando
    -1.00
     use
    -1.00
     digunakan
    -0.98
     použí
    -0.97
    POSITIVE LOGITS
     instead
    1.21
     from
    1.10
     hyvä
    1.06
     sparingly
    0.99
     for
    0.90
    endientes
    0.90
     вместо
    0.88
     invece
    0.88
     istället
    0.87
    instead
    0.87
    Activations Density 0.098%

    No Known Activations