© 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. 246355
    Prev
    Next
    INDEX
    Explanations

    also / också / och / juga / ogs / myöś

    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
     компонентов
    0.47
     кише
    0.47
    लि
    0.46
     protocols
    0.46
     preserv
    0.46
    洗
    0.46
    顶级
    0.45
    珩
    0.45
    кме
    0.45
     बुन
    0.45
    POSITIVE LOGITS
     naman
    0.55
     också
    0.54
     Aditya
    0.52
    oc
    0.50
     myös
    0.50
     أيضاً
    0.50
    off
    0.49
     juga
    0.49
     também
    0.48
     også
    0.48
    Activations Density 0.001%

    No Known Activations