© 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. 96559
    Prev
    Next
    INDEX
    Explanations

    government services and loans

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

    formatting for headings

    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
            
    0.47
     И
    0.47
    孪
    0.44
     पहुंचने
    0.44
     ONLY
    0.43
    uting
    0.43
    ဏ်
    0.43
    oxet
    0.41
    only
    0.41
     ========
    0.41
    POSITIVE LOGITS
     skip
    0.45
    IVI
    0.44
     Николай
    0.42
    логов
    0.41
     relentless
    0.40
    謎
    0.38
     mystery
    0.38
     sext
    0.38
     vélo
    0.38
    konom
    0.37
    Activations Density 0.000%

    No Known Activations