© 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. 193831
    Prev
    Next
    INDEX
    Explanations

    caused injury or infection

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

    historical or descriptive states

    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
    ش
    0.51
     takers
    0.47
     archaeologists
    0.46
     cannons
    0.46
    anesi
    0.46
    punctuation
    0.46
    ولی
    0.45
     crosses
    0.45
    ੰ
    0.45
    ابی
    0.44
    POSITIVE LOGITS
    <0x97>
    0.52
     Brü
    0.52
     ক্ষেত্র
    0.52
     fieldValue
    0.50
     મહિલા
    0.49
     Lehigh
    0.49
     Meghan
    0.48
     Knoxville
    0.48
     едно
    0.48
     材料
    0.48
    Activations Density 0.001%

    No Known Activations