© 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. 142246
    Prev
    Next
    INDEX
    Explanations

    specific prepositions and followed words

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

    future actions

    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
     preso
    0.49
     nessuno
    0.49
    最早
    0.49
     kişi
    0.46
     ܐ
    0.46
     loin
    0.46
     suhu
    0.45
    QCD
    0.44
    POS
    0.44
     presa
    0.43
    POSITIVE LOGITS
    âni
    0.43
     instanceof
    0.41
     создания
    0.41
    ꯋ
    0.41
     refocus
    0.41
    란
    0.41
    ne
    0.41
     प्रयास
    0.41
     файлы
    0.40
    ๔
    0.40
    Activations Density 0.001%

    No Known Activations