© 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. 20488
    Prev
    Next
    INDEX
    Explanations

    formation, fusion, plasma, stars

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

    star formation and nuclear fusion

    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
     प्रतिनिध
    0.47
     нарушения
    0.47
    ঞ্চলিক
    0.46
    眄
    0.45
     gắng
    0.44
     resection
    0.44
     कैलेंडर
    0.44
     violación
    0.44
     viagens
    0.43
    狒
    0.43
    POSITIVE LOGITS
    pro
    0.57
    プロ
    0.52
     protons
    0.52
    formation
    0.49
     formation
    0.49
    ignition
    0.48
     Neon
    0.47
    firebase
    0.46
     neon
    0.46
    hydrogen
    0.46
    Activations Density 0.022%

    No Known Activations