© 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. 35494
    Prev
    Next
    INDEX
    Explanations

    indices and benchmarks

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

    financial and economic indices

    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
     Jonah
    0.47
    Structuring
    0.44
     Einwill
    0.44
    垦
    0.43
     संभाव
    0.43
     Labrenzia
    0.42
     przyczyn
    0.41
     غور
    0.41
     conséquence
    0.41
     प्रॉफिट
    0.40
    POSITIVE LOGITS
     benchmark
    0.66
    index
    0.65
     index
    0.64
    basket
    0.64
     basket
    0.61
     Index
    0.59
     benchmarks
    0.59
     benchmarking
    0.54
    選
    0.54
    indice
    0.54
    Activations Density 0.055%

    No Known Activations