© 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. 34-GEMMASCOPE-RES-131K
    7. 59684
    Prev
    Next
    INDEX
    Explanations

    action by agent

    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
     môžete
    -2.14
     majú
    -2.08
     môžu
    -2.05
     känna
    -1.80
     budete
    -1.71
     läsa
    -1.70
     máte
    -1.70
     musíte
    -1.68
     budú
    -1.67
     dôle
    -1.66
    POSITIVE LOGITS
     by
    13.13
     توسط
    4.66
     oleh
    3.98
    by
    3.55
     tarafından
    3.44
     bởi
    3.05
     przez
    2.89
     द्वारा
    2.86
     بواسطة
    2.81
     By
    2.78
    Activations Density 1.589%

    No Known Activations