© 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. 175961
    Prev
    Next
    INDEX
    Explanations

    travel and locations

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

    abstract concepts and possibilities

    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
     existência
    0.47
    ேத்க
    0.46
     relações
    0.46
    싸
    0.45
    Җ
    0.45
     sàn
    0.45
     localização
    0.45
    𝙚
    0.45
     preguntar
    0.45
    ளிய
    0.44
    POSITIVE LOGITS
     UIS
    0.57
     Hawaii
    0.50
     Accounting
    0.49
     Treaty
    0.47
     Enforcement
    0.47
     Guam
    0.46
     Samoa
    0.46
     Mobility
    0.46
     UST
    0.46
     Vickers
    0.45
    Activations Density 0.001%

    No Known Activations