© 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. 151015
    Prev
    Next
    INDEX
    Explanations

    international currencies and locations

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

    varied significantly, available for, financial services

    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
     Архів
    0.49
     हंस
    0.46
     Arach
    0.46
     మి
    0.46
     Analysis
    0.45
     器
    0.45
     архів
    0.44
    embryon
    0.44
    रिडोर
    0.44
     说
    0.43
    POSITIVE LOGITS
     podr
    0.50
    Japanese
    0.50
    PK
    0.48
    PH
    0.46
    NEW
    0.45
    Harga
    0.44
    NHK
    0.44
     Jerman
    0.43
     Anda
    0.43
    3
    0.43
    Activations Density 0.000%

    No Known Activations