© 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. 49499
    Prev
    Next
    INDEX
    Explanations

    or while, to over

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

    orbital mechanics, academic degrees, email addresses

    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
     एनिमल्स
    0.45
    '+
    0.44
    жно
    0.43
    ڡ
    0.43
    sinx
    0.43
    िंग
    0.42
     tubules
    0.42
    쵸
    0.42
    옳
    0.42
    ዳ
    0.41
    POSITIVE LOGITS
     February
    0.48
     April
    0.46
     IM
    0.46
     disponibili
    0.45
     عام
    0.45
     advance
    0.44
     series
    0.43
     andere
    0.43
    लोगों
    0.43
     OCD
    0.43
    Activations Density 0.000%

    No Known Activations