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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4328
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    Assuming
    -0.80
     lần
    -0.77
     Commentaires
    -0.77
    kDa
    -0.76
    assuming
    -0.76
    Como
    -0.76
     месяца
    -0.76
    itamos
    -0.76
     assuming
    -0.74
    Ideally
    -0.74
    POSITIVE LOGITS
    ressible
    0.88
    یرات
    0.83
     comprar
    0.82
    演唱
    0.79
    تے
    0.75
     Schönheit
    0.75
    疋
    0.75
     pud
    0.74
     SOR
    0.73
    러나
    0.73
    Activations Density 0.049%

    No Known Activations