© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2225
    Prev
    Next
    INDEX
    Explanations

    future actions and possibilities

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

    verbs in Turkish, often in infinitive or possibility forms

    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
     थीं
    0.54
    なぜ
    0.52
     থাকুন
    0.50
     TouchUtils
    0.50
    㡺
    0.50
    杝
    0.49
    必ず
    0.48
    勎
    0.47
     ഉണ്ട്
    0.47
     नेहमी
    0.47
    POSITIVE LOGITS
    abilecek
    1.06
    ıyor
    0.97
    maktan
    0.96
    ması
    0.95
    acağ
    0.95
    acak
    0.94
    madan
    0.93
    abileceğ
    0.92
    iyor
    0.91
    maya
    0.91
    Activations Density 0.002%

    No Known Activations