© 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. 84606
    Prev
    Next
    INDEX
    Explanations

    second order coupled system

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

    severity, ease, or proportions

    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
     caméra
    0.50
     fondamental
    0.49
    ༢
    0.48
    宣传
    0.47
     dizajn
    0.45
     România
    0.44
    ılığı
    0.44
     kamera
    0.44
     comunitario
    0.44
     communauté
    0.43
    POSITIVE LOGITS
    曝
    0.43
     Severity
    0.42
     Obesity
    0.42
     ease
    0.41
     obesity
    0.41
     Incorrect
    0.41
     exposed
    0.40
     Ultraviolet
    0.40
    шку
    0.39
     perhaps
    0.39
    Activations Density 0.003%

    No Known Activations