© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204582
    Prev
    Next
    INDEX
    Explanations

    critical importance

    np_acts-logits-general · gemini-2.5-flash-lite

    internationalized text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    猊
    0.43
     বিলম্ব
    0.42
    setMessage
    0.42
    晁
    0.42
    dup
    0.42
     दुसरी
    0.42
    鰤
    0.41
    grep
    0.41
    อื่น
    0.41
    প্রাণ
    0.41
    POSITIVE LOGITS
     function
    0.50
     muchas
    0.50
     dapat
    0.49
     berken
    0.49
     fonction
    0.48
     ciudad
    0.47
     relevante
    0.47
     International
    0.47
     İ
    0.46
     willkommen
    0.46
    Activations Density 0.001%

    No Known Activations