© 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. 116589
    Prev
    Next
    INDEX
    Explanations

    stock market investments

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

    Risk of breaking and reporting

    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
     mods
    0.56
     noviembre
    0.54
     cristiano
    0.51
     creemos
    0.51
    ␊
    0.49
    髹
    0.49
     negros
    0.48
    
    0.48
     queryString
    0.47
     nonexpansive
    0.46
    POSITIVE LOGITS
    pel
    0.55
    ize
    0.54
    stone
    0.50
    burton
    0.50
    ention
    0.50
    OO
    0.50
    asia
    0.48
    ton
    0.47
    pal
    0.47
    aca
    0.47
    Activations Density 0.000%

    No Known Activations