© 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. 186492
    Prev
    Next
    INDEX
    Explanations

    Russians from

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

    career, job, or health advancement

    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
    OutputFile
    0.47
    Off
    0.47
    Offic
    0.46
    佳
    0.46
    Renk
    0.45
     awkwardly
    0.45
    फ
    0.45
    Mem
    0.44
    മു
    0.44
    체
    0.44
    POSITIVE LOGITS
     пои
    0.50
     hosting
    0.47
     hydrocarbons
    0.45
     bookstores
    0.42
     लोकांनी
    0.41
     campaigning
    0.41
     acquiring
    0.40
     Humanitarian
    0.40
     humanitarian
    0.40
     freeing
    0.40
    Activations Density 0.003%

    No Known Activations