© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5900
    Prev
    Next
    INDEX
    Explanations

    getting things done

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

    CLI access or getting information

    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_53_width_65k_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
     terdapat
    0.44
     regaining
    0.44
    っております
    0.43
     রয়ে
    0.42
     присутствует
    0.41
     bulunan
    0.40
    ก็ได้
    0.39
    至
    0.38
     మాన
    0.38
     جارہ
    0.38
    POSITIVE LOGITS
     done
    0.70
     outta
    0.61
    Done
    0.60
    done
    0.58
     refunded
    0.56
     facilement
    0.55
     DONE
    0.55
     traction
    0.55
     rapidement
    0.55
     gedaan
    0.55
    Activations Density 0.241%

    No Known Activations