© 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. 26008
    Prev
    Next
    INDEX
    Explanations

    films on graphene

    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
     Üniversitesi
    -1.18
     decidieron
    -1.06
    цький
    -1.04
    关键字
    -1.03
    Especificações
    -1.02
     foton
    -0.98
     иллюстрация
    -0.96
    ఠ
    -0.94
     摄影
    -0.94
     magnifiques
    -0.93
    POSITIVE LOGITS
     projects
    1.16
    煬
    1.07
     clients
    1.05
     magnético
    0.98
    quettes
    0.98
     peptides
    0.96
     elétrico
    0.96
     wichtigste
    0.96
     lakier
    0.96
    瀑布
    0.95
    Activations Density 0.069%

    No Known Activations