© 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. 145447
    Prev
    Next
    INDEX
    Explanations

    property types

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

    finance, washing, GPUs

    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
     treaties
    0.55
     greats
    0.53
     Lithuania
    0.52
    ਬ
    0.52
     Eighth
    0.51
     India
    0.50
     we
    0.48
     discontinue
    0.48
     communic
    0.48
     broken
    0.47
    POSITIVE LOGITS
     рома
    0.51
     рит
    0.47
    мови
    0.47
    вна
    0.47
     навчання
    0.45
     conduz
    0.45
     hẳn
    0.45
    摫
    0.44
    Là
    0.44
     পালা
    0.44
    Activations Density 0.001%

    No Known Activations