© 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. 156968
    Prev
    Next
    INDEX
    Explanations

    multilingual concepts

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

    violation, recovery, findings, safety, revolution

    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
    Weekly
    0.45
     longe
    0.44
     entered
    0.43
     entrer
    0.43
    择
    0.43
     Viitattu
    0.42
     interven
    0.42
    餓
    0.42
    ឈ
    0.42
    рук
    0.42
    POSITIVE LOGITS
     proporcionan
    0.49
     中国
    0.47
     美国
    0.47
     necesitan
    0.46
    iculata
    0.46
     Jawa
    0.46
    ্ঠ
    0.45
     चीन
    0.45
     집
    0.45
    melidir
    0.45
    Activations Density 0.002%

    No Known Activations