© 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. 220614
    Prev
    Next
    INDEX
    Explanations

    power and utilities market

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

    apostrophe, promise, speculation

    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
     HashTable
    0.49
     पं
    0.48
     இந்நிலையில்
    0.45
     incessantly
    0.45
    your
    0.45
    
    0.44
    asionally
    0.44
    এদিকে
    0.44
     worsen
    0.43
     Exchequer
    0.43
    POSITIVE LOGITS
     rol
    0.54
     rollover
    0.46
     blade
    0.46
     indig
    0.46
     elektri
    0.44
     ដើម្បី
    0.44
     texte
    0.43
     seta
    0.43
     v
    0.43
    qtd
    0.43
    Activations Density 0.001%

    No Known Activations