© 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. 109052
    Prev
    Next
    INDEX
    Explanations

    CAR-T therapies or cells

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

    conclusions resulting from conditions

    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
    ра
    0.54
    কে
    0.50
    ”、“
    0.45
    _
    0.44
    не
    0.44
    ру
    0.43
    н
    0.43
    ﺭ
    0.43
    WOOD
    0.43
    ंडर
    0.42
    POSITIVE LOGITS
     असल्याने
    0.64
     sehingga
    0.63
     joten
    0.57
     ಆದ್ದರಿಂದ
    0.56
     więc
    0.55
     cujo
    0.55
     sodass
    0.54
     nên
    0.53
     Therefore
    0.53
     też
    0.53
    Activations Density 0.002%

    No Known Activations