© 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. 34431
    Prev
    Next
    INDEX
    Explanations

    currency conversion for countries

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

    in + context

    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
     Cluster
    0.44
    דע
    0.41
     Kommunikation
    0.39
     Procedures
    0.38
    摔
    0.38
     Rotation
    0.38
     contrairement
    0.38
    Cluster
    0.37
     Procedure
    0.37
    指數
    0.36
    POSITIVE LOGITS
     novo
    0.45
     novi
    0.44
    赈
    0.44
     nova
    0.42
     dommages
    0.41
     metaphysical
    0.41
    其它
    0.40
     oni
    0.40
    麸
    0.40
     nový
    0.40
    Activations Density 0.001%

    No Known Activations