© 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. 231294
    Prev
    Next
    INDEX
    Explanations

    translated, systems, dose, year

    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
    стро
    0.54
    alan
    0.50
    alamat
    0.48
     ټ
    0.46
     filede
    0.46
    atani
    0.45
     خاط
    0.45
     AppBsky
    0.45
    еру
    0.44
    asını
    0.44
    POSITIVE LOGITS
     year
    0.53
    者
    0.50
     virus
    0.50
     Virus
    0.50
     दुर्लभ
    0.49
     homeopathic
    0.48
    year
    0.47
     Safe
    0.46
     साल
    0.46
     Consumption
    0.46
    Activations Density 0.003%

    No Known Activations