© 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. 2366
    Prev
    Next
    INDEX
    Explanations

    actions and requests

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

    Korean language translation

    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
     மருத்துவ
    0.44
     பொதுவாக
    0.41
    ંબ
    0.39
     имеют
    0.38
     பெரும்பாலும்
    0.38
    generally
    0.37
     և
    0.36
     வணிக
    0.36
    [
    0.36
     underlies
    0.36
    POSITIVE LOGITS
    想要
    0.53
     possa
    0.49
     pueda
    0.48
     بتوان
    0.47
     sneaky
    0.46
     cheeky
    0.46
     একটু
    0.45
    拿出
    0.44
     langsung
    0.44
    哪怕
    0.43
    Activations Density 0.028%

    No Known Activations