© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14641
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     wartawan
    -0.91
    tető
    -0.90
     вероятно
    -0.90
     memimpin
    -0.89
     började
    -0.89
     pemimpin
    -0.89
    зидент
    -0.89
    🌷
    -0.89
    着一个
    -0.88
    lated
    -0.88
    POSITIVE LOGITS
     and
    1.27
     partager
    0.90
    Penulis
    0.90
    できない
    0.88
    yeni
    0.87
    López
    0.85
    vertret
    0.85
     wn
    0.85
     fría
    0.85
    Naam
    0.84
    Activations Density 0.002%

    No Known Activations