© 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. 193853
    Prev
    Next
    INDEX
    Explanations

    celebrate

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

    celebration, power units, religious topics

    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
    <0x1D>
    0.47
    栀
    0.47
    最新的
    0.45
     Macbook
    0.43
    最新
    0.42
     Latest
    0.41
    Թ
    0.41
    ⒏
    0.41
    think
    0.41
    狨
    0.41
    POSITIVE LOGITS
     célébr
    0.45
     celebra
    0.44
     celebrar
    0.43
     celebration
    0.42
     pauper
    0.41
    nPortIndex
    0.41
     celebración
    0.40
     masing
    0.40
     célé
    0.39
     ampla
    0.39
    Activations Density 0.000%

    No Known Activations