© 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. 245786
    Prev
    Next
    INDEX
    Explanations

    Paul Joseph Records

    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
     complicating
    0.48
     complicates
    0.46
    пута
    0.44
    有两种
    0.44
    棦
    0.43
     labored
    0.43
    继
    0.43
    Cham
    0.42
    Manisha
    0.42
    olve
    0.42
    POSITIVE LOGITS
     (=
    0.46
     एक्सपेक्ट
    0.45
     टेक्स्ट
    0.45
     gastronomic
    0.44
     Xiaomi
    0.43
     hit
    0.42
     TEXT
    0.42
     ALL
    0.42
     फ्ल
    0.42
     উদ
    0.42
    Activations Density 0.002%

    No Known Activations