© 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. 122581
    Prev
    Next
    INDEX
    Explanations

    stock exchange

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

    Laplace smoothing

    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
     bữa
    0.53
    μένες
    0.50
     skyrocketed
    0.47
     spalle
    0.46
    olí
    0.45
    Ợ
    0.45
     सोनी
    0.44
     bı
    0.43
    мові
    0.42
     molde
    0.42
    POSITIVE LOGITS
    闼
    0.57
    Adder
    0.49
    、
    0.48
     android
    0.47
     Credits
    0.47
     habitation
    0.46
     Lister
    0.46
     Matthias
    0.45
     Cela
    0.45
     Algorithm
    0.44
    Activations Density 0.000%

    No Known Activations