© 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. 242026
    Prev
    Next
    INDEX
    Explanations

    legal context or specific regulations

    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
     decontamination
    0.55
     constitutional
    0.49
     عم
    0.47
    addField
    0.46
     flap
    0.46
     ي
    0.45
     mate
    0.45
     resurgence
    0.45
     maxHeight
    0.44
     hurricanes
    0.44
    POSITIVE LOGITS
    𝖽
    0.53
    Roses
    0.52
    Dias
    0.50
    Foi
    0.48
     hrane
    0.47
    З
    0.46
    Eu
    0.46
    Etat
    0.45
    México
    0.45
     ताब्यात
    0.44
    Activations Density 0.000%

    No Known Activations