© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10048
    Prev
    Next
    INDEX
    Explanations

    Fedora

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

    list comprehensions

    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_40_width_16k_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
    epin
    0.45
     พูด
    0.42
     डिस्क्रिप्शन
    0.42
     deadlines
    0.39
    โค
    0.39
    تا
    0.39
    }||
    0.38
    row
    0.38
    紜
    0.38
     recount
    0.37
    POSITIVE LOGITS
     fed
    0.47
     FED
    0.44
     живут
    0.43
     FRE
    0.42
    ўкі
    0.42
     Stoke
    0.42
     насла
    0.41
     feder
    0.40
     Meir
    0.40
     Fedora
    0.39
    Activations Density 0.029%

    No Known Activations