© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65404
    Prev
    Next
    INDEX
    Explanations

    technical terms and systems

    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
    และ
    -1.11
    上午
    -1.08
     this
    -1.05
    还会
    -1.02
    tance
    -1.00
     insgesamt
    -0.99
     membantu
    -0.95
     Innenstadt
    -0.95
     fanfiction
    -0.95
     our
    -0.94
    POSITIVE LOGITS
    点此
    1.11
    新华
    1.05
     inva
    1.04
    ograf
    1.02
    过来了
    1.01
     notor
    1.00
     gloria
    1.00
     galer
    0.99
     luminos
    0.99
    こんばん
    0.98
    Activations Density 0.214%

    No Known Activations