© 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. 9738
    Prev
    Next
    INDEX
    Explanations

    relapsing fever research

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

    academic publication links

    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
    ᓛ
    0.54
    
    0.52
    让自己
    0.50
     कौर
    0.49
     बांट
    0.48
    राने
    0.48
     अक्त
    0.48
     तलैया
    0.48
    娆
    0.48
    μου
    0.48
    POSITIVE LOGITS
     interdiscipl
    0.62
     research
    0.56
     Research
    0.55
     Invited
    0.51
    的研究
    0.49
    0.48
     study
    0.48
     studies
    0.48
     Forschung
    0.47
     RESEARCH
    0.47
    Activations Density 0.019%

    No Known Activations